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

Dataset: Open Web Text

Neuron 416 in Layer 6

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: 3.0427. Min Range: -3.0427

Max Act: 3.0427. Min Act: -0.1700

Data Index: 1317871 (Open Web Text)

Max Activating Token Index: 129

Text #1

Max Range: 3.0427. Min Range: -3.0427

Max Act: 3.0129. Min Act: -0.1700

Data Index: 239929 (Open Web Text)

Max Activating Token Index: 261

Text #2

Max Range: 3.0427. Min Range: -3.0427

Max Act: 3.0239. Min Act: -0.1700

Data Index: 8143224 (Open Web Text)

Max Activating Token Index: 751

Text #3

Max Range: 3.0427. Min Range: -3.0427

Max Act: 3.0255. Min Act: -0.1700

Data Index: 2607694 (Open Web Text)

Max Activating Token Index: 378

Text #4

Max Range: 3.0427. Min Range: -3.0427

Max Act: 2.9898. Min Act: -0.1700

Data Index: 2202298 (Open Web Text)

Max Activating Token Index: 689

Text #5

Max Range: 3.0427. Min Range: -3.0427

Max Act: 2.9735. Min Act: -0.1700

Data Index: 2096618 (Open Web Text)

Max Activating Token Index: 378

Text #6

Max Range: 3.0427. Min Range: -3.0427

Max Act: 2.9888. Min Act: -0.1700

Data Index: 5321232 (Open Web Text)

Max Activating Token Index: 597

Text #7

Max Range: 3.0427. Min Range: -3.0427

Max Act: 2.9626. Min Act: -0.1700

Data Index: 5183891 (Open Web Text)

Max Activating Token Index: 395

Text #8

Max Range: 3.0427. Min Range: -3.0427

Max Act: 2.9688. Min Act: -0.1700

Data Index: 5527094 (Open Web Text)

Max Activating Token Index: 503

Text #9

Max Range: 3.0427. Min Range: -3.0427

Max Act: 2.9752. Min Act: -0.1700

Data Index: 2332523 (Open Web Text)

Max Activating Token Index: 966

Text #10

Max Range: 3.0427. Min Range: -3.0427

Max Act: 2.9544. Min Act: -0.1700

Data Index: 2883261 (Open Web Text)

Max Activating Token Index: 899

Text #11

Max Range: 3.0427. Min Range: -3.0427

Max Act: 2.9557. Min Act: -0.1700

Data Index: 2909053 (Open Web Text)

Max Activating Token Index: 611

Text #12

Max Range: 3.0427. Min Range: -3.0427

Max Act: 2.9384. Min Act: -0.1700

Data Index: 7158401 (Open Web Text)

Max Activating Token Index: 548

Text #13

Max Range: 3.0427. Min Range: -3.0427

Max Act: 2.9490. Min Act: -0.1700

Data Index: 1041005 (Open Web Text)

Max Activating Token Index: 579

Text #14

Max Range: 3.0427. Min Range: -3.0427

Max Act: 2.8912. Min Act: -0.1700

Data Index: 2602969 (Open Web Text)

Max Activating Token Index: 733

Text #15

Max Range: 3.0427. Min Range: -3.0427

Max Act: 2.9316. Min Act: -0.1700

Data Index: 2299668 (Open Web Text)

Max Activating Token Index: 453

Text #16

Max Range: 3.0427. Min Range: -3.0427

Max Act: 2.9161. Min Act: -0.1700

Data Index: 3973718 (Open Web Text)

Max Activating Token Index: 627

Text #17

Max Range: 3.0427. Min Range: -3.0427

Max Act: 2.9238. Min Act: -0.1700

Data Index: 6344374 (Open Web Text)

Max Activating Token Index: 470

Text #18

Max Range: 3.0427. Min Range: -3.0427

Max Act: 2.8803. Min Act: -0.1700

Data Index: 7562895 (Open Web Text)

Max Activating Token Index: 74

Text #19

Max Range: 3.0427. Min Range: -3.0427

Max Act: 2.8898. Min Act: -0.1700

Data Index: 1382250 (Open Web Text)

Max Activating Token Index: 93