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

Dataset: Open Web Text

Neuron 1660 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: 3.8107. Min Range: -3.8107

Max Act: 3.8107. Min Act: -0.1700

Data Index: 1099963 (Open Web Text)

Max Activating Token Index: 6

Text #1

Max Range: 3.8107. Min Range: -3.8107

Max Act: 3.8022. Min Act: -0.1700

Data Index: 3040282 (Open Web Text)

Max Activating Token Index: 799

Text #2

Max Range: 3.8107. Min Range: -3.8107

Max Act: 3.7893. Min Act: -0.1700

Data Index: 7491400 (Open Web Text)

Max Activating Token Index: 502

Text #3

Max Range: 3.8107. Min Range: -3.8107

Max Act: 3.7667. Min Act: -0.1700

Data Index: 8368897 (Open Web Text)

Max Activating Token Index: 43

Text #4

Max Range: 3.8107. Min Range: -3.8107

Max Act: 3.7712. Min Act: -0.1700

Data Index: 7854486 (Open Web Text)

Max Activating Token Index: 946

Text #5

Max Range: 3.8107. Min Range: -3.8107

Max Act: 3.7745. Min Act: -0.1700

Data Index: 5824988 (Open Web Text)

Max Activating Token Index: 778

Text #6

Max Range: 3.8107. Min Range: -3.8107

Max Act: 3.7768. Min Act: -0.1700

Data Index: 1460954 (Open Web Text)

Max Activating Token Index: 854

Text #7

Max Range: 3.8107. Min Range: -3.8107

Max Act: 3.7700. Min Act: -0.1700

Data Index: 8370319 (Open Web Text)

Max Activating Token Index: 296

Text #8

Max Range: 3.8107. Min Range: -3.8107

Max Act: 3.7598. Min Act: -0.1700

Data Index: 3556543 (Open Web Text)

Max Activating Token Index: 530

Text #9

Max Range: 3.8107. Min Range: -3.8107

Max Act: 3.7679. Min Act: -0.1700

Data Index: 571296 (Open Web Text)

Max Activating Token Index: 706

Text #10

Max Range: 3.8107. Min Range: -3.8107

Max Act: 3.7476. Min Act: -0.1700

Data Index: 1329316 (Open Web Text)

Max Activating Token Index: 21

Text #11

Max Range: 3.8107. Min Range: -3.8107

Max Act: 3.7442. Min Act: -0.1700

Data Index: 4797891 (Open Web Text)

Max Activating Token Index: 280

Text #12

Max Range: 3.8107. Min Range: -3.8107

Max Act: 3.7502. Min Act: -0.1700

Data Index: 5111370 (Open Web Text)

Max Activating Token Index: 794

Text #13

Max Range: 3.8107. Min Range: -3.8107

Max Act: 3.7443. Min Act: -0.1700

Data Index: 484853 (Open Web Text)

Max Activating Token Index: 862

Text #14

Max Range: 3.8107. Min Range: -3.8107

Max Act: 3.7467. Min Act: -0.1700

Data Index: 5485304 (Open Web Text)

Max Activating Token Index: 814

Text #15

Max Range: 3.8107. Min Range: -3.8107

Max Act: 3.7292. Min Act: -0.1700

Data Index: 1966409 (Open Web Text)

Max Activating Token Index: 751

Text #16

Max Range: 3.8107. Min Range: -3.8107

Max Act: 3.7367. Min Act: -0.1700

Data Index: 6504596 (Open Web Text)

Max Activating Token Index: 39

Text #17

Max Range: 3.8107. Min Range: -3.8107

Max Act: 3.7451. Min Act: -0.1700

Data Index: 6974711 (Open Web Text)

Max Activating Token Index: 35

Text #18

Max Range: 3.8107. Min Range: -3.8107

Max Act: 3.7436. Min Act: -0.1700

Data Index: 7235408 (Open Web Text)

Max Activating Token Index: 10

Text #19

Max Range: 3.8107. Min Range: -3.8107

Max Act: 3.7377. Min Act: -0.1700

Data Index: 7713395 (Open Web Text)

Max Activating Token Index: 768