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

Dataset: Open Web Text

Neuron 2106 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: 4.4315. Min Range: -4.4315

Max Act: 4.4315. Min Act: -0.1700

Data Index: 8592804 (Open Web Text)

Max Activating Token Index: 817

Text #1

Max Range: 4.4315. Min Range: -4.4315

Max Act: 4.3687. Min Act: -0.1700

Data Index: 6527761 (Open Web Text)

Max Activating Token Index: 34

Text #2

Max Range: 4.4315. Min Range: -4.4315

Max Act: 4.3607. Min Act: -0.1700

Data Index: 5991759 (Open Web Text)

Max Activating Token Index: 974

Text #3

Max Range: 4.4315. Min Range: -4.4315

Max Act: 4.3615. Min Act: -0.1700

Data Index: 8377865 (Open Web Text)

Max Activating Token Index: 286

Text #4

Max Range: 4.4315. Min Range: -4.4315

Max Act: 4.3048. Min Act: -0.1700

Data Index: 861322 (Open Web Text)

Max Activating Token Index: 15

Text #5

Max Range: 4.4315. Min Range: -4.4315

Max Act: 4.2570. Min Act: -0.1700

Data Index: 1927481 (Open Web Text)

Max Activating Token Index: 880

Text #6

Max Range: 4.4315. Min Range: -4.4315

Max Act: 4.2925. Min Act: -0.1700

Data Index: 6073240 (Open Web Text)

Max Activating Token Index: 813

Text #7

Max Range: 4.4315. Min Range: -4.4315

Max Act: 4.2567. Min Act: -0.1700

Data Index: 1495583 (Open Web Text)

Max Activating Token Index: 147

Text #8

Max Range: 4.4315. Min Range: -4.4315

Max Act: 4.2488. Min Act: -0.1700

Data Index: 3943585 (Open Web Text)

Max Activating Token Index: 57

Text #9

Max Range: 4.4315. Min Range: -4.4315

Max Act: 4.2431. Min Act: -0.1700

Data Index: 763239 (Open Web Text)

Max Activating Token Index: 387

Text #10

Max Range: 4.4315. Min Range: -4.4315

Max Act: 4.2478. Min Act: -0.1700

Data Index: 3663121 (Open Web Text)

Max Activating Token Index: 113

Text #11

Max Range: 4.4315. Min Range: -4.4315

Max Act: 4.2551. Min Act: -0.1700

Data Index: 7728323 (Open Web Text)

Max Activating Token Index: 480

Text #12

Max Range: 4.4315. Min Range: -4.4315

Max Act: 4.2462. Min Act: -0.1700

Data Index: 1264606 (Open Web Text)

Max Activating Token Index: 12

Text #13

Max Range: 4.4315. Min Range: -4.4315

Max Act: 4.2345. Min Act: -0.1700

Data Index: 2431349 (Open Web Text)

Max Activating Token Index: 84

Text #14

Max Range: 4.4315. Min Range: -4.4315

Max Act: 4.2293. Min Act: -0.1700

Data Index: 2409580 (Open Web Text)

Max Activating Token Index: 29

Text #15

Max Range: 4.4315. Min Range: -4.4315

Max Act: 4.2502. Min Act: -0.1700

Data Index: 7136450 (Open Web Text)

Max Activating Token Index: 614

Text #16

Max Range: 4.4315. Min Range: -4.4315

Max Act: 4.2301. Min Act: -0.1700

Data Index: 2106648 (Open Web Text)

Max Activating Token Index: 97

Text #17

Max Range: 4.4315. Min Range: -4.4315

Max Act: 4.2585. Min Act: -0.1700

Data Index: 14994 (Open Web Text)

Max Activating Token Index: 412

Text #18

Max Range: 4.4315. Min Range: -4.4315

Max Act: 4.2160. Min Act: -0.1700

Data Index: 324125 (Open Web Text)

Max Activating Token Index: 708

Text #19

Max Range: 4.4315. Min Range: -4.4315

Max Act: 4.2073. Min Act: -0.1700

Data Index: 2094905 (Open Web Text)

Max Activating Token Index: 150