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

Dataset: Open Web Text

Neuron 1929 in Layer 1

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: 3.3987. Min Range: -3.3987

Max Act: 3.3987. Min Act: -0.1700

Data Index: 4783524 (Open Web Text)

Max Activating Token Index: 203

Text #1

Max Range: 3.3987. Min Range: -3.3987

Max Act: 3.3640. Min Act: -0.1700

Data Index: 8475061 (Open Web Text)

Max Activating Token Index: 118

Text #2

Max Range: 3.3987. Min Range: -3.3987

Max Act: 3.3643. Min Act: -0.1700

Data Index: 5105758 (Open Web Text)

Max Activating Token Index: 489

Text #3

Max Range: 3.3987. Min Range: -3.3987

Max Act: 3.3377. Min Act: -0.1700

Data Index: 5960558 (Open Web Text)

Max Activating Token Index: 108

Text #4

Max Range: 3.3987. Min Range: -3.3987

Max Act: 3.3516. Min Act: -0.1700

Data Index: 802549 (Open Web Text)

Max Activating Token Index: 110

Text #5

Max Range: 3.3987. Min Range: -3.3987

Max Act: 3.3325. Min Act: -0.1700

Data Index: 6453039 (Open Web Text)

Max Activating Token Index: 72

Text #6

Max Range: 3.3987. Min Range: -3.3987

Max Act: 3.3299. Min Act: -0.1700

Data Index: 8482891 (Open Web Text)

Max Activating Token Index: 6

Text #7

Max Range: 3.3987. Min Range: -3.3987

Max Act: 3.3116. Min Act: -0.1700

Data Index: 8329284 (Open Web Text)

Max Activating Token Index: 525

Text #8

Max Range: 3.3987. Min Range: -3.3987

Max Act: 3.3142. Min Act: -0.1700

Data Index: 7021459 (Open Web Text)

Max Activating Token Index: 520

Text #9

Max Range: 3.3987. Min Range: -3.3987

Max Act: 3.3099. Min Act: -0.1700

Data Index: 4328308 (Open Web Text)

Max Activating Token Index: 65

Text #10

Max Range: 3.3987. Min Range: -3.3987

Max Act: 3.3133. Min Act: -0.1700

Data Index: 7558822 (Open Web Text)

Max Activating Token Index: 28

Text #11

Max Range: 3.3987. Min Range: -3.3987

Max Act: 3.3098. Min Act: -0.1700

Data Index: 7971070 (Open Web Text)

Max Activating Token Index: 79

Text #12

Max Range: 3.3987. Min Range: -3.3987

Max Act: 3.3079. Min Act: -0.1700

Data Index: 2904541 (Open Web Text)

Max Activating Token Index: 624

Text #13

Max Range: 3.3987. Min Range: -3.3987

Max Act: 3.2918. Min Act: -0.1700

Data Index: 2730665 (Open Web Text)

Max Activating Token Index: 660

Text #14

Max Range: 3.3987. Min Range: -3.3987

Max Act: 3.3087. Min Act: -0.1700

Data Index: 4614331 (Open Web Text)

Max Activating Token Index: 420

Text #15

Max Range: 3.3987. Min Range: -3.3987

Max Act: 3.2954. Min Act: -0.1700

Data Index: 3441523 (Open Web Text)

Max Activating Token Index: 89

Text #16

Max Range: 3.3987. Min Range: -3.3987

Max Act: 3.2841. Min Act: -0.1700

Data Index: 3745205 (Open Web Text)

Max Activating Token Index: 276

Text #17

Max Range: 3.3987. Min Range: -3.3987

Max Act: 3.2866. Min Act: -0.1700

Data Index: 1409756 (Open Web Text)

Max Activating Token Index: 601

Text #18

Max Range: 3.3987. Min Range: -3.3987

Max Act: 3.2801. Min Act: -0.1700

Data Index: 1201114 (Open Web Text)

Max Activating Token Index: 95

Text #19

Max Range: 3.3987. Min Range: -3.3987

Max Act: 3.2865. Min Act: -0.1700

Data Index: 1979415 (Open Web Text)

Max Activating Token Index: 473