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

Dataset: Open Web Text

Neuron 2182 in Layer 2

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: 4.8514. Min Range: -4.8514

Max Act: 4.8514. Min Act: -0.1700

Data Index: 3000581 (Open Web Text)

Max Activating Token Index: 494

Text #1

Max Range: 4.8514. Min Range: -4.8514

Max Act: 4.7889. Min Act: -0.1700

Data Index: 3417907 (Open Web Text)

Max Activating Token Index: 802

Text #2

Max Range: 4.8514. Min Range: -4.8514

Max Act: 4.7958. Min Act: -0.1700

Data Index: 48834 (Open Web Text)

Max Activating Token Index: 385

Text #3

Max Range: 4.8514. Min Range: -4.8514

Max Act: 4.7605. Min Act: -0.1700

Data Index: 2920979 (Open Web Text)

Max Activating Token Index: 543

Text #4

Max Range: 4.8514. Min Range: -4.8514

Max Act: 4.7562. Min Act: -0.1700

Data Index: 338296 (Open Web Text)

Max Activating Token Index: 440

Text #5

Max Range: 4.8514. Min Range: -4.8514

Max Act: 4.7640. Min Act: -0.1700

Data Index: 3881168 (Open Web Text)

Max Activating Token Index: 472

Text #6

Max Range: 4.8514. Min Range: -4.8514

Max Act: 4.7406. Min Act: -0.1700

Data Index: 7893904 (Open Web Text)

Max Activating Token Index: 525

Text #7

Max Range: 4.8514. Min Range: -4.8514

Max Act: 4.7599. Min Act: -0.1700

Data Index: 7412725 (Open Web Text)

Max Activating Token Index: 962

Text #8

Max Range: 4.8514. Min Range: -4.8514

Max Act: 4.7191. Min Act: -0.1700

Data Index: 2460414 (Open Web Text)

Max Activating Token Index: 573

Text #9

Max Range: 4.8514. Min Range: -4.8514

Max Act: 4.6871. Min Act: -0.1700

Data Index: 2174803 (Open Web Text)

Max Activating Token Index: 659

Text #10

Max Range: 4.8514. Min Range: -4.8514

Max Act: 4.7403. Min Act: -0.1700

Data Index: 7060837 (Open Web Text)

Max Activating Token Index: 267

Text #11

Max Range: 4.8514. Min Range: -4.8514

Max Act: 4.7121. Min Act: -0.1700

Data Index: 6018349 (Open Web Text)

Max Activating Token Index: 1008

Text #12

Max Range: 4.8514. Min Range: -4.8514

Max Act: 4.7291. Min Act: -0.1700

Data Index: 4659778 (Open Web Text)

Max Activating Token Index: 567

Text #13

Max Range: 4.8514. Min Range: -4.8514

Max Act: 4.7027. Min Act: -0.1700

Data Index: 775751 (Open Web Text)

Max Activating Token Index: 433

Text #14

Max Range: 4.8514. Min Range: -4.8514

Max Act: 4.6993. Min Act: -0.1700

Data Index: 1955113 (Open Web Text)

Max Activating Token Index: 640

Text #15

Max Range: 4.8514. Min Range: -4.8514

Max Act: 4.6970. Min Act: -0.1700

Data Index: 8025688 (Open Web Text)

Max Activating Token Index: 860

Text #16

Max Range: 4.8514. Min Range: -4.8514

Max Act: 4.7202. Min Act: -0.1700

Data Index: 8689633 (Open Web Text)

Max Activating Token Index: 564

Text #17

Max Range: 4.8514. Min Range: -4.8514

Max Act: 4.6566. Min Act: -0.1700

Data Index: 5160334 (Open Web Text)

Max Activating Token Index: 471

Text #18

Max Range: 4.8514. Min Range: -4.8514

Max Act: 4.6550. Min Act: -0.1700

Data Index: 1028568 (Open Web Text)

Max Activating Token Index: 609

Text #19

Max Range: 4.8514. Min Range: -4.8514

Max Act: 4.7060. Min Act: -0.1700

Data Index: 3123577 (Open Web Text)

Max Activating Token Index: 497