< Prev | Home | Model | Random | Next >

Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer

Dataset: Open Web Text

Neuron 6374 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')



Text #0

Max Range: 4.8032. Min Range: -4.8032

Max Act: 4.8032. Min Act: -0.1700

Data Index: 5514364 (Open Web Text)

Max Activating Token Index: 634

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 4.8032. Min Range: -4.8032

Max Act: 4.7407. Min Act: -0.1700

Data Index: 34544 (Open Web Text)

Max Activating Token Index: 914

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 4.8032. Min Range: -4.8032

Max Act: 4.7407. Min Act: -0.1700

Data Index: 2768777 (Open Web Text)

Max Activating Token Index: 307

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 4.8032. Min Range: -4.8032

Max Act: 4.5845. Min Act: -0.1700

Data Index: 1455608 (Open Web Text)

Max Activating Token Index: 612

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 4.8032. Min Range: -4.8032

Max Act: 4.5220. Min Act: -0.1700

Data Index: 93303 (Open Web Text)

Max Activating Token Index: 368

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 4.8032. Min Range: -4.8032

Max Act: 4.5220. Min Act: -0.1700

Data Index: 5578778 (Open Web Text)

Max Activating Token Index: 320

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 4.8032. Min Range: -4.8032

Max Act: 4.5532. Min Act: -0.1700

Data Index: 2032193 (Open Web Text)

Max Activating Token Index: 21

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 4.8032. Min Range: -4.8032

Max Act: 4.5220. Min Act: -0.1700

Data Index: 6936312 (Open Web Text)

Max Activating Token Index: 584

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 4.8032. Min Range: -4.8032

Max Act: 4.4907. Min Act: -0.1700

Data Index: 3037741 (Open Web Text)

Max Activating Token Index: 137

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 4.8032. Min Range: -4.8032

Max Act: 4.4595. Min Act: -0.1700

Data Index: 2908259 (Open Web Text)

Max Activating Token Index: 425

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 4.8032. Min Range: -4.8032

Max Act: 4.4595. Min Act: -0.1700

Data Index: 2913069 (Open Web Text)

Max Activating Token Index: 277

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 4.8032. Min Range: -4.8032

Max Act: 4.4595. Min Act: -0.1700

Data Index: 4787543 (Open Web Text)

Max Activating Token Index: 107

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 4.8032. Min Range: -4.8032

Max Act: 4.3969. Min Act: -0.1700

Data Index: 5525394 (Open Web Text)

Max Activating Token Index: 709

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 4.8032. Min Range: -4.8032

Max Act: 4.4595. Min Act: -0.1700

Data Index: 640128 (Open Web Text)

Max Activating Token Index: 67

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 4.8032. Min Range: -4.8032

Max Act: 4.4282. Min Act: -0.1700

Data Index: 8699696 (Open Web Text)

Max Activating Token Index: 312

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 4.8032. Min Range: -4.8032

Max Act: 4.4282. Min Act: -0.1700

Data Index: 93308 (Open Web Text)

Max Activating Token Index: 41

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 4.8032. Min Range: -4.8032

Max Act: 4.4282. Min Act: -0.1700

Data Index: 8699694 (Open Web Text)

Max Activating Token Index: 134

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 4.8032. Min Range: -4.8032

Max Act: 4.3969. Min Act: -0.1700

Data Index: 2591796 (Open Web Text)

Max Activating Token Index: 169

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 4.8032. Min Range: -4.8032

Max Act: 4.3969. Min Act: -0.1700

Data Index: 5514365 (Open Web Text)

Max Activating Token Index: 548

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 4.8032. Min Range: -4.8032

Max Act: 4.3969. Min Act: -0.1700

Data Index: 6458628 (Open Web Text)

Max Activating Token Index: 466

Click toggle to see full text

Truncated

Full Text #19