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

Dataset: Open Web Text

Neuron 3000 in Layer 4

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: 4.3336. Min Range: -4.3336

Max Act: 4.2925. Min Act: -0.1700

Data Index: 4939632 (Open Web Text)

Max Activating Token Index: 601

Text #1

Max Range: 4.3336. Min Range: -4.3336

Max Act: 4.3336. Min Act: -0.1700

Data Index: 6795645 (Open Web Text)

Max Activating Token Index: 859

Text #2

Max Range: 4.3336. Min Range: -4.3336

Max Act: 4.3205. Min Act: -0.1700

Data Index: 7681648 (Open Web Text)

Max Activating Token Index: 107

Text #3

Max Range: 4.3336. Min Range: -4.3336

Max Act: 4.2318. Min Act: -0.1700

Data Index: 218965 (Open Web Text)

Max Activating Token Index: 76

Text #4

Max Range: 4.3336. Min Range: -4.3336

Max Act: 4.2413. Min Act: -0.1700

Data Index: 5234162 (Open Web Text)

Max Activating Token Index: 327

Text #5

Max Range: 4.3336. Min Range: -4.3336

Max Act: 4.2485. Min Act: -0.1700

Data Index: 7618870 (Open Web Text)

Max Activating Token Index: 237

Text #6

Max Range: 4.3336. Min Range: -4.3336

Max Act: 4.2170. Min Act: -0.1700

Data Index: 1391454 (Open Web Text)

Max Activating Token Index: 136

Text #7

Max Range: 4.3336. Min Range: -4.3336

Max Act: 4.1980. Min Act: -0.1700

Data Index: 75681 (Open Web Text)

Max Activating Token Index: 186

Text #8

Max Range: 4.3336. Min Range: -4.3336

Max Act: 4.1446. Min Act: -0.1700

Data Index: 7446274 (Open Web Text)

Max Activating Token Index: 450

Text #9

Max Range: 4.3336. Min Range: -4.3336

Max Act: 4.1703. Min Act: -0.1700

Data Index: 8832332 (Open Web Text)

Max Activating Token Index: 700

Text #10

Max Range: 4.3336. Min Range: -4.3336

Max Act: 4.1507. Min Act: -0.1700

Data Index: 2795391 (Open Web Text)

Max Activating Token Index: 286

Text #11

Max Range: 4.3336. Min Range: -4.3336

Max Act: 4.1626. Min Act: -0.1700

Data Index: 6543996 (Open Web Text)

Max Activating Token Index: 85

Text #12

Max Range: 4.3336. Min Range: -4.3336

Max Act: 4.1743. Min Act: -0.1700

Data Index: 5075772 (Open Web Text)

Max Activating Token Index: 986

Text #13

Max Range: 4.3336. Min Range: -4.3336

Max Act: 4.1741. Min Act: -0.1700

Data Index: 2238874 (Open Web Text)

Max Activating Token Index: 344

Text #14

Max Range: 4.3336. Min Range: -4.3336

Max Act: 4.1225. Min Act: -0.1700

Data Index: 3991191 (Open Web Text)

Max Activating Token Index: 425

Text #15

Max Range: 4.3336. Min Range: -4.3336

Max Act: 4.1569. Min Act: -0.1700

Data Index: 3802055 (Open Web Text)

Max Activating Token Index: 648

Text #16

Max Range: 4.3336. Min Range: -4.3336

Max Act: 4.1517. Min Act: -0.1700

Data Index: 865341 (Open Web Text)

Max Activating Token Index: 307

Text #17

Max Range: 4.3336. Min Range: -4.3336

Max Act: 4.1330. Min Act: -0.1700

Data Index: 1823689 (Open Web Text)

Max Activating Token Index: 657

Text #18

Max Range: 4.3336. Min Range: -4.3336

Max Act: 4.1321. Min Act: -0.1700

Data Index: 1958967 (Open Web Text)

Max Activating Token Index: 315

Text #19

Max Range: 4.3336. Min Range: -4.3336

Max Act: 4.1377. Min Act: -0.1700

Data Index: 5000348 (Open Web Text)

Max Activating Token Index: 426