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

Dataset: Open Web Text

Neuron 680 in Layer 3

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: 3.2826. Min Range: -3.2826

Max Act: 3.2826. Min Act: -0.1700

Data Index: 3926576 (Open Web Text)

Max Activating Token Index: 658

Text #1

Max Range: 3.2826. Min Range: -3.2826

Max Act: 3.2275. Min Act: -0.1700

Data Index: 4259171 (Open Web Text)

Max Activating Token Index: 645

Text #2

Max Range: 3.2826. Min Range: -3.2826

Max Act: 3.2115. Min Act: -0.1700

Data Index: 5434566 (Open Web Text)

Max Activating Token Index: 699

Text #3

Max Range: 3.2826. Min Range: -3.2826

Max Act: 3.2014. Min Act: -0.1700

Data Index: 7665571 (Open Web Text)

Max Activating Token Index: 594

Text #4

Max Range: 3.2826. Min Range: -3.2826

Max Act: 3.1784. Min Act: -0.1700

Data Index: 5811853 (Open Web Text)

Max Activating Token Index: 602

Text #5

Max Range: 3.2826. Min Range: -3.2826

Max Act: 3.1821. Min Act: -0.1700

Data Index: 7717958 (Open Web Text)

Max Activating Token Index: 703

Text #6

Max Range: 3.2826. Min Range: -3.2826

Max Act: 3.1779. Min Act: -0.1700

Data Index: 2778428 (Open Web Text)

Max Activating Token Index: 981

Text #7

Max Range: 3.2826. Min Range: -3.2826

Max Act: 3.1529. Min Act: -0.1700

Data Index: 5917387 (Open Web Text)

Max Activating Token Index: 710

Text #8

Max Range: 3.2826. Min Range: -3.2826

Max Act: 3.1534. Min Act: -0.1700

Data Index: 8738679 (Open Web Text)

Max Activating Token Index: 587

Text #9

Max Range: 3.2826. Min Range: -3.2826

Max Act: 3.1684. Min Act: -0.1700

Data Index: 2200942 (Open Web Text)

Max Activating Token Index: 797

Text #10

Max Range: 3.2826. Min Range: -3.2826

Max Act: 3.1162. Min Act: -0.1700

Data Index: 1153299 (Open Web Text)

Max Activating Token Index: 527

Text #11

Max Range: 3.2826. Min Range: -3.2826

Max Act: 3.1258. Min Act: -0.1700

Data Index: 6532884 (Open Web Text)

Max Activating Token Index: 717

Text #12

Max Range: 3.2826. Min Range: -3.2826

Max Act: 3.1128. Min Act: -0.1700

Data Index: 1838334 (Open Web Text)

Max Activating Token Index: 381

Text #13

Max Range: 3.2826. Min Range: -3.2826

Max Act: 3.1203. Min Act: -0.1700

Data Index: 1535212 (Open Web Text)

Max Activating Token Index: 483

Text #14

Max Range: 3.2826. Min Range: -3.2826

Max Act: 3.0928. Min Act: -0.1700

Data Index: 6100710 (Open Web Text)

Max Activating Token Index: 611

Text #15

Max Range: 3.2826. Min Range: -3.2826

Max Act: 3.0868. Min Act: -0.1700

Data Index: 621530 (Open Web Text)

Max Activating Token Index: 729

Text #16

Max Range: 3.2826. Min Range: -3.2826

Max Act: 3.1023. Min Act: -0.1700

Data Index: 6170049 (Open Web Text)

Max Activating Token Index: 741

Text #17

Max Range: 3.2826. Min Range: -3.2826

Max Act: 3.0933. Min Act: -0.1700

Data Index: 5881776 (Open Web Text)

Max Activating Token Index: 104

Text #18

Max Range: 3.2826. Min Range: -3.2826

Max Act: 3.0719. Min Act: -0.1700

Data Index: 2075550 (Open Web Text)

Max Activating Token Index: 729

Text #19

Max Range: 3.2826. Min Range: -3.2826

Max Act: 3.0883. Min Act: -0.1700

Data Index: 1432905 (Open Web Text)

Max Activating Token Index: 598