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

Dataset: Open Web Text

Neuron 976 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: 3.4670. Min Range: -3.4670

Max Act: 3.4670. Min Act: -0.1700

Data Index: 1774036 (Open Web Text)

Max Activating Token Index: 385

Text #1

Max Range: 3.4670. Min Range: -3.4670

Max Act: 3.4334. Min Act: -0.1700

Data Index: 230001 (Open Web Text)

Max Activating Token Index: 138

Text #2

Max Range: 3.4670. Min Range: -3.4670

Max Act: 3.4317. Min Act: -0.1700

Data Index: 1774040 (Open Web Text)

Max Activating Token Index: 838

Text #3

Max Range: 3.4670. Min Range: -3.4670

Max Act: 3.3777. Min Act: -0.1700

Data Index: 4136660 (Open Web Text)

Max Activating Token Index: 301

Text #4

Max Range: 3.4670. Min Range: -3.4670

Max Act: 3.3567. Min Act: -0.1700

Data Index: 5312159 (Open Web Text)

Max Activating Token Index: 417

Text #5

Max Range: 3.4670. Min Range: -3.4670

Max Act: 3.3067. Min Act: -0.1700

Data Index: 3401940 (Open Web Text)

Max Activating Token Index: 11

Text #6

Max Range: 3.4670. Min Range: -3.4670

Max Act: 3.3180. Min Act: -0.1700

Data Index: 1063441 (Open Web Text)

Max Activating Token Index: 776

Text #7

Max Range: 3.4670. Min Range: -3.4670

Max Act: 3.3189. Min Act: -0.1700

Data Index: 7613987 (Open Web Text)

Max Activating Token Index: 630

Text #8

Max Range: 3.4670. Min Range: -3.4670

Max Act: 3.3001. Min Act: -0.1700

Data Index: 3150071 (Open Web Text)

Max Activating Token Index: 557

Text #9

Max Range: 3.4670. Min Range: -3.4670

Max Act: 3.3195. Min Act: -0.1700

Data Index: 2622698 (Open Web Text)

Max Activating Token Index: 403

Text #10

Max Range: 3.4670. Min Range: -3.4670

Max Act: 3.3272. Min Act: -0.1700

Data Index: 79897 (Open Web Text)

Max Activating Token Index: 522

Text #11

Max Range: 3.4670. Min Range: -3.4670

Max Act: 3.2698. Min Act: -0.1700

Data Index: 3401975 (Open Web Text)

Max Activating Token Index: 177

Text #12

Max Range: 3.4670. Min Range: -3.4670

Max Act: 3.2864. Min Act: -0.1700

Data Index: 3401943 (Open Web Text)

Max Activating Token Index: 1023

Text #13

Max Range: 3.4670. Min Range: -3.4670

Max Act: 3.2779. Min Act: -0.1700

Data Index: 7175345 (Open Web Text)

Max Activating Token Index: 612

Text #14

Max Range: 3.4670. Min Range: -3.4670

Max Act: 3.2842. Min Act: -0.1700

Data Index: 6077740 (Open Web Text)

Max Activating Token Index: 315

Text #15

Max Range: 3.4670. Min Range: -3.4670

Max Act: 3.2589. Min Act: -0.1700

Data Index: 6077739 (Open Web Text)

Max Activating Token Index: 553

Text #16

Max Range: 3.4670. Min Range: -3.4670

Max Act: 3.2530. Min Act: -0.1700

Data Index: 8813525 (Open Web Text)

Max Activating Token Index: 1009

Text #17

Max Range: 3.4670. Min Range: -3.4670

Max Act: 3.2523. Min Act: -0.1700

Data Index: 3348965 (Open Web Text)

Max Activating Token Index: 684

Text #18

Max Range: 3.4670. Min Range: -3.4670

Max Act: 3.2434. Min Act: -0.1700

Data Index: 1774041 (Open Web Text)

Max Activating Token Index: 437

Text #19

Max Range: 3.4670. Min Range: -3.4670

Max Act: 3.2304. Min Act: -0.1700

Data Index: 3401945 (Open Web Text)

Max Activating Token Index: 25