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

Dataset: Open Web Text

Neuron 817 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: 4.7820. Min Range: -4.7820

Max Act: 4.7820. Min Act: -0.1700

Data Index: 4896863 (Open Web Text)

Max Activating Token Index: 477

Text #1

Max Range: 4.7820. Min Range: -4.7820

Max Act: 4.7475. Min Act: -0.1700

Data Index: 2318622 (Open Web Text)

Max Activating Token Index: 521

Text #2

Max Range: 4.7820. Min Range: -4.7820

Max Act: 4.7349. Min Act: -0.1700

Data Index: 1989692 (Open Web Text)

Max Activating Token Index: 75

Text #3

Max Range: 4.7820. Min Range: -4.7820

Max Act: 4.6978. Min Act: -0.1700

Data Index: 8194889 (Open Web Text)

Max Activating Token Index: 298

Text #4

Max Range: 4.7820. Min Range: -4.7820

Max Act: 4.7058. Min Act: -0.1700

Data Index: 2569735 (Open Web Text)

Max Activating Token Index: 371

Text #5

Max Range: 4.7820. Min Range: -4.7820

Max Act: 4.7116. Min Act: -0.1700

Data Index: 7621389 (Open Web Text)

Max Activating Token Index: 584

Text #6

Max Range: 4.7820. Min Range: -4.7820

Max Act: 4.6986. Min Act: -0.1700

Data Index: 6692941 (Open Web Text)

Max Activating Token Index: 311

Text #7

Max Range: 4.7820. Min Range: -4.7820

Max Act: 4.6794. Min Act: -0.1700

Data Index: 6596058 (Open Web Text)

Max Activating Token Index: 275

Text #8

Max Range: 4.7820. Min Range: -4.7820

Max Act: 4.6803. Min Act: -0.1700

Data Index: 6667541 (Open Web Text)

Max Activating Token Index: 723

Text #9

Max Range: 4.7820. Min Range: -4.7820

Max Act: 4.6823. Min Act: -0.1700

Data Index: 6337978 (Open Web Text)

Max Activating Token Index: 421

Text #10

Max Range: 4.7820. Min Range: -4.7820

Max Act: 4.6757. Min Act: -0.1700

Data Index: 2327925 (Open Web Text)

Max Activating Token Index: 588

Text #11

Max Range: 4.7820. Min Range: -4.7820

Max Act: 4.7064. Min Act: -0.1700

Data Index: 7396264 (Open Web Text)

Max Activating Token Index: 108

Text #12

Max Range: 4.7820. Min Range: -4.7820

Max Act: 4.7082. Min Act: -0.1700

Data Index: 3853682 (Open Web Text)

Max Activating Token Index: 559

Text #13

Max Range: 4.7820. Min Range: -4.7820

Max Act: 4.6784. Min Act: -0.1700

Data Index: 6190499 (Open Web Text)

Max Activating Token Index: 581

Text #14

Max Range: 4.7820. Min Range: -4.7820

Max Act: 4.6835. Min Act: -0.1700

Data Index: 4503127 (Open Web Text)

Max Activating Token Index: 443

Text #15

Max Range: 4.7820. Min Range: -4.7820

Max Act: 4.6937. Min Act: -0.1700

Data Index: 8177704 (Open Web Text)

Max Activating Token Index: 683

Text #16

Max Range: 4.7820. Min Range: -4.7820

Max Act: 4.6976. Min Act: -0.1700

Data Index: 4534929 (Open Web Text)

Max Activating Token Index: 516

Text #17

Max Range: 4.7820. Min Range: -4.7820

Max Act: 4.6988. Min Act: -0.1700

Data Index: 2872603 (Open Web Text)

Max Activating Token Index: 153

Text #18

Max Range: 4.7820. Min Range: -4.7820

Max Act: 4.6871. Min Act: -0.1700

Data Index: 6031118 (Open Web Text)

Max Activating Token Index: 454

Text #19

Max Range: 4.7820. Min Range: -4.7820

Max Act: 4.6762. Min Act: -0.1700

Data Index: 5697679 (Open Web Text)

Max Activating Token Index: 248