Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 1246 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 3.6466. Min Range: -3.6466

Max Act: 3.6466. Min Act: -0.1700

Data Index: 1365084 (Open Web Text)

Max Activating Token Index: 849

Text #1

Max Range: 3.6466. Min Range: -3.6466

Max Act: 3.5478. Min Act: -0.1700

Data Index: 3975414 (Open Web Text)

Max Activating Token Index: 6

Text #2

Max Range: 3.6466. Min Range: -3.6466

Max Act: 3.5112. Min Act: -0.1700

Data Index: 2195680 (Open Web Text)

Max Activating Token Index: 5

Text #3

Max Range: 3.6466. Min Range: -3.6466

Max Act: 3.4891. Min Act: -0.1700

Data Index: 1959561 (Open Web Text)

Max Activating Token Index: 3

Text #4

Max Range: 3.6466. Min Range: -3.6466

Max Act: 3.4652. Min Act: -0.1700

Data Index: 2626192 (Open Web Text)

Max Activating Token Index: 10

Text #5

Max Range: 3.6466. Min Range: -3.6466

Max Act: 3.4617. Min Act: -0.1700

Data Index: 3884061 (Open Web Text)

Max Activating Token Index: 2

Text #6

Max Range: 3.6466. Min Range: -3.6466

Max Act: 3.4468. Min Act: -0.1700

Data Index: 8021391 (Open Web Text)

Max Activating Token Index: 4

Text #7

Max Range: 3.6466. Min Range: -3.6466

Max Act: 3.4627. Min Act: -0.1700

Data Index: 2369607 (Open Web Text)

Max Activating Token Index: 6

Text #8

Max Range: 3.6466. Min Range: -3.6466

Max Act: 3.4360. Min Act: -0.1700

Data Index: 3977773 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 3.6466. Min Range: -3.6466

Max Act: 3.4303. Min Act: -0.1700

Data Index: 4560393 (Open Web Text)

Max Activating Token Index: 17

Text #10

Max Range: 3.6466. Min Range: -3.6466

Max Act: 3.4270. Min Act: -0.1700

Data Index: 3419543 (Open Web Text)

Max Activating Token Index: 11

Text #11

Max Range: 3.6466. Min Range: -3.6466

Max Act: 3.4216. Min Act: -0.1700

Data Index: 7303137 (Open Web Text)

Max Activating Token Index: 11

Text #12

Max Range: 3.6466. Min Range: -3.6466

Max Act: 3.4256. Min Act: -0.1700

Data Index: 805260 (Open Web Text)

Max Activating Token Index: 17

Text #13

Max Range: 3.6466. Min Range: -3.6466

Max Act: 3.4292. Min Act: -0.1700

Data Index: 5175040 (Open Web Text)

Max Activating Token Index: 9

Text #14

Max Range: 3.6466. Min Range: -3.6466

Max Act: 3.4419. Min Act: -0.1700

Data Index: 4123308 (Open Web Text)

Max Activating Token Index: 10

Text #15

Max Range: 3.6466. Min Range: -3.6466

Max Act: 3.4025. Min Act: -0.1700

Data Index: 2936508 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 3.6466. Min Range: -3.6466

Max Act: 3.3913. Min Act: -0.1700

Data Index: 3380508 (Open Web Text)

Max Activating Token Index: 3

Text #17

Max Range: 3.6466. Min Range: -3.6466

Max Act: 3.4083. Min Act: -0.1700

Data Index: 3299053 (Open Web Text)

Max Activating Token Index: 2

Text #18

Max Range: 3.6466. Min Range: -3.6466

Max Act: 3.4083. Min Act: -0.1700

Data Index: 638061 (Open Web Text)

Max Activating Token Index: 2

Text #19

Max Range: 3.6466. Min Range: -3.6466

Max Act: 3.4045. Min Act: -0.1700

Data Index: 2985623 (Open Web Text)

Max Activating Token Index: 8