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

Dataset: Open Web Text

Neuron 1541 in Layer 1

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: 1.6980. Min Range: -1.6980

Max Act: 1.6980. Min Act: -0.1700

Data Index: 8676288 (Open Web Text)

Max Activating Token Index: 20

Text #1

Max Range: 1.6980. Min Range: -1.6980

Max Act: 1.6803. Min Act: -0.1700

Data Index: 1381266 (Open Web Text)

Max Activating Token Index: 522

Text #2

Max Range: 1.6980. Min Range: -1.6980

Max Act: 1.6766. Min Act: -0.1700

Data Index: 3366812 (Open Web Text)

Max Activating Token Index: 25

Text #3

Max Range: 1.6980. Min Range: -1.6980

Max Act: 1.6732. Min Act: -0.1700

Data Index: 976400 (Open Web Text)

Max Activating Token Index: 76

Text #4

Max Range: 1.6980. Min Range: -1.6980

Max Act: 1.6639. Min Act: -0.1700

Data Index: 6977657 (Open Web Text)

Max Activating Token Index: 200

Text #5

Max Range: 1.6980. Min Range: -1.6980

Max Act: 1.6750. Min Act: -0.1700

Data Index: 115423 (Open Web Text)

Max Activating Token Index: 955

Text #6

Max Range: 1.6980. Min Range: -1.6980

Max Act: 1.6534. Min Act: -0.1700

Data Index: 7364990 (Open Web Text)

Max Activating Token Index: 15

Text #7

Max Range: 1.6980. Min Range: -1.6980

Max Act: 1.6499. Min Act: -0.1700

Data Index: 5585063 (Open Web Text)

Max Activating Token Index: 219

Text #8

Max Range: 1.6980. Min Range: -1.6980

Max Act: 1.6509. Min Act: -0.1700

Data Index: 2732271 (Open Web Text)

Max Activating Token Index: 645

Text #9

Max Range: 1.6980. Min Range: -1.6980

Max Act: 1.6477. Min Act: -0.1700

Data Index: 804857 (Open Web Text)

Max Activating Token Index: 92

Text #10

Max Range: 1.6980. Min Range: -1.6980

Max Act: 1.6440. Min Act: -0.1700

Data Index: 4762442 (Open Web Text)

Max Activating Token Index: 34

Text #11

Max Range: 1.6980. Min Range: -1.6980

Max Act: 1.6437. Min Act: -0.1700

Data Index: 3407022 (Open Web Text)

Max Activating Token Index: 178

Text #12

Max Range: 1.6980. Min Range: -1.6980

Max Act: 1.6401. Min Act: -0.1700

Data Index: 7759020 (Open Web Text)

Max Activating Token Index: 472

Text #13

Max Range: 1.6980. Min Range: -1.6980

Max Act: 1.6376. Min Act: -0.1700

Data Index: 2396824 (Open Web Text)

Max Activating Token Index: 340

Text #14

Max Range: 1.6980. Min Range: -1.6980

Max Act: 1.6395. Min Act: -0.1700

Data Index: 5923079 (Open Web Text)

Max Activating Token Index: 957

Text #15

Max Range: 1.6980. Min Range: -1.6980

Max Act: 1.6371. Min Act: -0.1700

Data Index: 6873263 (Open Web Text)

Max Activating Token Index: 526

Text #16

Max Range: 1.6980. Min Range: -1.6980

Max Act: 1.6314. Min Act: -0.1700

Data Index: 3487329 (Open Web Text)

Max Activating Token Index: 324

Text #17

Max Range: 1.6980. Min Range: -1.6980

Max Act: 1.6361. Min Act: -0.1700

Data Index: 709232 (Open Web Text)

Max Activating Token Index: 136

Text #18

Max Range: 1.6980. Min Range: -1.6980

Max Act: 1.6329. Min Act: -0.1700

Data Index: 1889221 (Open Web Text)

Max Activating Token Index: 119

Text #19

Max Range: 1.6980. Min Range: -1.6980

Max Act: 1.6322. Min Act: -0.1699

Data Index: 8664255 (Open Web Text)

Max Activating Token Index: 563