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

Dataset: Open Web Text

Neuron 1042 in Layer 3

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: 4.4033. Min Range: -4.4033

Max Act: 4.4033. Min Act: -0.1700

Data Index: 1175932 (Open Web Text)

Max Activating Token Index: 233

Text #1

Max Range: 4.4033. Min Range: -4.4033

Max Act: 4.3955. Min Act: -0.1700

Data Index: 7071466 (Open Web Text)

Max Activating Token Index: 280

Text #2

Max Range: 4.4033. Min Range: -4.4033

Max Act: 4.3615. Min Act: -0.1700

Data Index: 2483108 (Open Web Text)

Max Activating Token Index: 606

Text #3

Max Range: 4.4033. Min Range: -4.4033

Max Act: 4.3374. Min Act: -0.1700

Data Index: 6968724 (Open Web Text)

Max Activating Token Index: 612

Text #4

Max Range: 4.4033. Min Range: -4.4033

Max Act: 4.2603. Min Act: -0.1700

Data Index: 6250829 (Open Web Text)

Max Activating Token Index: 354

Text #5

Max Range: 4.4033. Min Range: -4.4033

Max Act: 4.2807. Min Act: -0.1700

Data Index: 7111876 (Open Web Text)

Max Activating Token Index: 116

Text #6

Max Range: 4.4033. Min Range: -4.4033

Max Act: 4.2444. Min Act: -0.1700

Data Index: 8265767 (Open Web Text)

Max Activating Token Index: 970

Text #7

Max Range: 4.4033. Min Range: -4.4033

Max Act: 4.2824. Min Act: -0.1700

Data Index: 6248367 (Open Web Text)

Max Activating Token Index: 489

Text #8

Max Range: 4.4033. Min Range: -4.4033

Max Act: 4.2406. Min Act: -0.1700

Data Index: 7895898 (Open Web Text)

Max Activating Token Index: 1007

Text #9

Max Range: 4.4033. Min Range: -4.4033

Max Act: 4.2544. Min Act: -0.1700

Data Index: 2114673 (Open Web Text)

Max Activating Token Index: 665

Text #10

Max Range: 4.4033. Min Range: -4.4033

Max Act: 4.2487. Min Act: -0.1700

Data Index: 548068 (Open Web Text)

Max Activating Token Index: 881

Text #11

Max Range: 4.4033. Min Range: -4.4033

Max Act: 4.2522. Min Act: -0.1700

Data Index: 794241 (Open Web Text)

Max Activating Token Index: 481

Text #12

Max Range: 4.4033. Min Range: -4.4033

Max Act: 4.2130. Min Act: -0.1700

Data Index: 7683366 (Open Web Text)

Max Activating Token Index: 911

Text #13

Max Range: 4.4033. Min Range: -4.4033

Max Act: 4.2315. Min Act: -0.1700

Data Index: 1276943 (Open Web Text)

Max Activating Token Index: 191

Text #14

Max Range: 4.4033. Min Range: -4.4033

Max Act: 4.2120. Min Act: -0.1700

Data Index: 2616433 (Open Web Text)

Max Activating Token Index: 87

Text #15

Max Range: 4.4033. Min Range: -4.4033

Max Act: 4.2071. Min Act: -0.1700

Data Index: 1761788 (Open Web Text)

Max Activating Token Index: 516

Text #16

Max Range: 4.4033. Min Range: -4.4033

Max Act: 4.2231. Min Act: -0.1700

Data Index: 1208343 (Open Web Text)

Max Activating Token Index: 933

Text #17

Max Range: 4.4033. Min Range: -4.4033

Max Act: 4.1968. Min Act: -0.1700

Data Index: 6834004 (Open Web Text)

Max Activating Token Index: 95

Text #18

Max Range: 4.4033. Min Range: -4.4033

Max Act: 4.1969. Min Act: -0.1700

Data Index: 287226 (Open Web Text)

Max Activating Token Index: 642

Text #19

Max Range: 4.4033. Min Range: -4.4033

Max Act: 4.1801. Min Act: -0.1700

Data Index: 1104177 (Open Web Text)

Max Activating Token Index: 916