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

Dataset: Open Web Text

Neuron 954 in Layer 2

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: 5.0886. Min Range: -5.0886

Max Act: 5.0886. Min Act: -0.1700

Data Index: 3470527 (Open Web Text)

Max Activating Token Index: 862

Text #1

Max Range: 5.0886. Min Range: -5.0886

Max Act: 4.9893. Min Act: -0.1700

Data Index: 6007273 (Open Web Text)

Max Activating Token Index: 538

Text #2

Max Range: 5.0886. Min Range: -5.0886

Max Act: 5.0552. Min Act: -0.1700

Data Index: 5324914 (Open Web Text)

Max Activating Token Index: 171

Text #3

Max Range: 5.0886. Min Range: -5.0886

Max Act: 5.0476. Min Act: -0.1698

Data Index: 7481208 (Open Web Text)

Max Activating Token Index: 406

Text #4

Max Range: 5.0886. Min Range: -5.0886

Max Act: 4.9558. Min Act: -0.1700

Data Index: 5845824 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 5.0886. Min Range: -5.0886

Max Act: 4.9265. Min Act: -0.1700

Data Index: 8134355 (Open Web Text)

Max Activating Token Index: 516

Text #6

Max Range: 5.0886. Min Range: -5.0886

Max Act: 4.9282. Min Act: -0.1698

Data Index: 1913816 (Open Web Text)

Max Activating Token Index: 515

Text #7

Max Range: 5.0886. Min Range: -5.0886

Max Act: 4.9326. Min Act: -0.1700

Data Index: 788153 (Open Web Text)

Max Activating Token Index: 524

Text #8

Max Range: 5.0886. Min Range: -5.0886

Max Act: 4.9032. Min Act: -0.1698

Data Index: 3347231 (Open Web Text)

Max Activating Token Index: 177

Text #9

Max Range: 5.0886. Min Range: -5.0886

Max Act: 4.9301. Min Act: -0.1700

Data Index: 3653115 (Open Web Text)

Max Activating Token Index: 368

Text #10

Max Range: 5.0886. Min Range: -5.0886

Max Act: 4.8574. Min Act: -0.1700

Data Index: 7987398 (Open Web Text)

Max Activating Token Index: 875

Text #11

Max Range: 5.0886. Min Range: -5.0886

Max Act: 4.8826. Min Act: -0.1698

Data Index: 3713527 (Open Web Text)

Max Activating Token Index: 996

Text #12

Max Range: 5.0886. Min Range: -5.0886

Max Act: 4.9379. Min Act: -0.1700

Data Index: 3143180 (Open Web Text)

Max Activating Token Index: 69

Text #13

Max Range: 5.0886. Min Range: -5.0886

Max Act: 4.8301. Min Act: -0.1699

Data Index: 645503 (Open Web Text)

Max Activating Token Index: 232

Text #14

Max Range: 5.0886. Min Range: -5.0886

Max Act: 4.8853. Min Act: -0.1700

Data Index: 6125365 (Open Web Text)

Max Activating Token Index: 532

Text #15

Max Range: 5.0886. Min Range: -5.0886

Max Act: 4.8334. Min Act: -0.1616

Data Index: 1215203 (Open Web Text)

Max Activating Token Index: 80

Text #16

Max Range: 5.0886. Min Range: -5.0886

Max Act: 4.8582. Min Act: -0.1698

Data Index: 2890149 (Open Web Text)

Max Activating Token Index: 664

Text #17

Max Range: 5.0886. Min Range: -5.0886

Max Act: 4.8635. Min Act: -0.1698

Data Index: 6206047 (Open Web Text)

Max Activating Token Index: 483

Text #18

Max Range: 5.0886. Min Range: -5.0886

Max Act: 4.9115. Min Act: -0.1700

Data Index: 3439924 (Open Web Text)

Max Activating Token Index: 753

Text #19

Max Range: 5.0886. Min Range: -5.0886

Max Act: 4.7613. Min Act: -0.1700

Data Index: 5436847 (Open Web Text)

Max Activating Token Index: 458