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

Dataset: Open Web Text

Neuron 1891 in Layer 4

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: 2.1971. Min Range: -2.1971

Max Act: 2.1971. Min Act: -0.1700

Data Index: 8112561 (Open Web Text)

Max Activating Token Index: 604

Text #1

Max Range: 2.1971. Min Range: -2.1971

Max Act: 2.1667. Min Act: -0.1700

Data Index: 8033287 (Open Web Text)

Max Activating Token Index: 716

Text #2

Max Range: 2.1971. Min Range: -2.1971

Max Act: 2.1424. Min Act: -0.1700

Data Index: 8530848 (Open Web Text)

Max Activating Token Index: 572

Text #3

Max Range: 2.1971. Min Range: -2.1971

Max Act: 2.1260. Min Act: -0.1700

Data Index: 1893398 (Open Web Text)

Max Activating Token Index: 988

Text #4

Max Range: 2.1971. Min Range: -2.1971

Max Act: 2.1029. Min Act: -0.1700

Data Index: 8727102 (Open Web Text)

Max Activating Token Index: 477

Text #5

Max Range: 2.1971. Min Range: -2.1971

Max Act: 2.0824. Min Act: -0.1700

Data Index: 5662154 (Open Web Text)

Max Activating Token Index: 369

Text #6

Max Range: 2.1971. Min Range: -2.1971

Max Act: 2.0569. Min Act: -0.1700

Data Index: 3355628 (Open Web Text)

Max Activating Token Index: 939

Text #7

Max Range: 2.1971. Min Range: -2.1971

Max Act: 2.0656. Min Act: -0.1700

Data Index: 2585276 (Open Web Text)

Max Activating Token Index: 200

Text #8

Max Range: 2.1971. Min Range: -2.1971

Max Act: 2.0568. Min Act: -0.1700

Data Index: 267796 (Open Web Text)

Max Activating Token Index: 563

Text #9

Max Range: 2.1971. Min Range: -2.1971

Max Act: 2.0486. Min Act: -0.1700

Data Index: 787881 (Open Web Text)

Max Activating Token Index: 986

Text #10

Max Range: 2.1971. Min Range: -2.1971

Max Act: 2.0509. Min Act: -0.1700

Data Index: 8545549 (Open Web Text)

Max Activating Token Index: 1021

Text #11

Max Range: 2.1971. Min Range: -2.1971

Max Act: 2.0593. Min Act: -0.1700

Data Index: 2769356 (Open Web Text)

Max Activating Token Index: 336

Text #12

Max Range: 2.1971. Min Range: -2.1971

Max Act: 2.0528. Min Act: -0.1700

Data Index: 3620473 (Open Web Text)

Max Activating Token Index: 4

Text #13

Max Range: 2.1971. Min Range: -2.1971

Max Act: 2.0551. Min Act: -0.1700

Data Index: 5194221 (Open Web Text)

Max Activating Token Index: 702

Text #14

Max Range: 2.1971. Min Range: -2.1971

Max Act: 2.0246. Min Act: -0.1700

Data Index: 4313003 (Open Web Text)

Max Activating Token Index: 614

Text #15

Max Range: 2.1971. Min Range: -2.1971

Max Act: 2.0564. Min Act: -0.1700

Data Index: 4213000 (Open Web Text)

Max Activating Token Index: 866

Text #16

Max Range: 2.1971. Min Range: -2.1971

Max Act: 2.0501. Min Act: -0.1700

Data Index: 6317848 (Open Web Text)

Max Activating Token Index: 513

Text #17

Max Range: 2.1971. Min Range: -2.1971

Max Act: 2.0332. Min Act: -0.1700

Data Index: 6317853 (Open Web Text)

Max Activating Token Index: 563

Text #18

Max Range: 2.1971. Min Range: -2.1971

Max Act: 2.0598. Min Act: -0.1700

Data Index: 6054067 (Open Web Text)

Max Activating Token Index: 550

Text #19

Max Range: 2.1971. Min Range: -2.1971

Max Act: 2.0340. Min Act: -0.1700

Data Index: 3587572 (Open Web Text)

Max Activating Token Index: 483