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

Dataset: Open Web Text

Neuron 840 in Layer 0

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: 4.5703. Min Range: -4.5703

Max Act: 4.5703. Min Act: -0.1700

Data Index: 5494419 (Open Web Text)

Max Activating Token Index: 70

Text #1

Max Range: 4.5703. Min Range: -4.5703

Max Act: 4.4764. Min Act: -0.1700

Data Index: 3625909 (Open Web Text)

Max Activating Token Index: 854

Text #2

Max Range: 4.5703. Min Range: -4.5703

Max Act: 4.4225. Min Act: -0.1700

Data Index: 3568663 (Open Web Text)

Max Activating Token Index: 592

Text #3

Max Range: 4.5703. Min Range: -4.5703

Max Act: 4.4072. Min Act: -0.1700

Data Index: 7416931 (Open Web Text)

Max Activating Token Index: 347

Text #4

Max Range: 4.5703. Min Range: -4.5703

Max Act: 4.3902. Min Act: -0.1700

Data Index: 5715923 (Open Web Text)

Max Activating Token Index: 300

Text #5

Max Range: 4.5703. Min Range: -4.5703

Max Act: 4.4037. Min Act: -0.1700

Data Index: 3427788 (Open Web Text)

Max Activating Token Index: 654

Text #6

Max Range: 4.5703. Min Range: -4.5703

Max Act: 4.3950. Min Act: -0.1700

Data Index: 8002476 (Open Web Text)

Max Activating Token Index: 938

Text #7

Max Range: 4.5703. Min Range: -4.5703

Max Act: 4.3713. Min Act: -0.1700

Data Index: 3156493 (Open Web Text)

Max Activating Token Index: 61

Text #8

Max Range: 4.5703. Min Range: -4.5703

Max Act: 4.3651. Min Act: -0.1700

Data Index: 6629059 (Open Web Text)

Max Activating Token Index: 816

Text #9

Max Range: 4.5703. Min Range: -4.5703

Max Act: 4.3678. Min Act: -0.1700

Data Index: 6402329 (Open Web Text)

Max Activating Token Index: 896

Text #10

Max Range: 4.5703. Min Range: -4.5703

Max Act: 4.3298. Min Act: -0.1700

Data Index: 406253 (Open Web Text)

Max Activating Token Index: 602

Text #11

Max Range: 4.5703. Min Range: -4.5703

Max Act: 4.3356. Min Act: -0.1700

Data Index: 2988689 (Open Web Text)

Max Activating Token Index: 658

Text #12

Max Range: 4.5703. Min Range: -4.5703

Max Act: 4.3120. Min Act: -0.1700

Data Index: 8028087 (Open Web Text)

Max Activating Token Index: 844

Text #13

Max Range: 4.5703. Min Range: -4.5703

Max Act: 4.3360. Min Act: -0.1700

Data Index: 3727855 (Open Web Text)

Max Activating Token Index: 154

Text #14

Max Range: 4.5703. Min Range: -4.5703

Max Act: 4.3414. Min Act: -0.1700

Data Index: 7511240 (Open Web Text)

Max Activating Token Index: 45

Text #15

Max Range: 4.5703. Min Range: -4.5703

Max Act: 4.3284. Min Act: -0.1700

Data Index: 6123904 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 4.5703. Min Range: -4.5703

Max Act: 4.3298. Min Act: -0.1700

Data Index: 7228624 (Open Web Text)

Max Activating Token Index: 292

Text #17

Max Range: 4.5703. Min Range: -4.5703

Max Act: 4.3218. Min Act: -0.1700

Data Index: 5195711 (Open Web Text)

Max Activating Token Index: 500

Text #18

Max Range: 4.5703. Min Range: -4.5703

Max Act: 4.3266. Min Act: -0.1700

Data Index: 6724620 (Open Web Text)

Max Activating Token Index: 544

Text #19

Max Range: 4.5703. Min Range: -4.5703

Max Act: 4.3156. Min Act: -0.1700

Data Index: 2445022 (Open Web Text)

Max Activating Token Index: 314