Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3055 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0513. Min Range: -0.0513

Max Act: 0.0513. Min Act: -0.0003

Data Index: 461724 (C4 (Web Text))

Max Activating Token Index: 925

Text #1

Max Range: 0.0513. Min Range: -0.0513

Max Act: 0.0500. Min Act: -0.0003

Data Index: 856046 (C4 (Web Text))

Max Activating Token Index: 966

Text #2

Max Range: 0.0513. Min Range: -0.0513

Max Act: 0.0472. Min Act: -0.0003

Data Index: 338690 (C4 (Web Text))

Max Activating Token Index: 980

Text #3

Max Range: 0.0513. Min Range: -0.0513

Max Act: 0.0471. Min Act: -0.0003

Data Index: 678258 (C4 (Web Text))

Max Activating Token Index: 981

Text #4

Max Range: 0.0513. Min Range: -0.0513

Max Act: 0.0368. Min Act: -0.0003

Data Index: 1350326 (C4 (Web Text))

Max Activating Token Index: 871

Text #5

Max Range: 0.0513. Min Range: -0.0513

Max Act: 0.0446. Min Act: -0.0003

Data Index: 1158706 (C4 (Web Text))

Max Activating Token Index: 689

Text #6

Max Range: 0.0513. Min Range: -0.0513

Max Act: 0.0422. Min Act: -0.0003

Data Index: 268206 (C4 (Web Text))

Max Activating Token Index: 103

Text #7

Max Range: 0.0513. Min Range: -0.0513

Max Act: 0.0420. Min Act: -0.0003

Data Index: 73679 (C4 (Web Text))

Max Activating Token Index: 938

Text #8

Max Range: 0.0513. Min Range: -0.0513

Max Act: 0.0415. Min Act: -0.0003

Data Index: 1080336 (C4 (Web Text))

Max Activating Token Index: 973

Text #9

Max Range: 0.0513. Min Range: -0.0513

Max Act: 0.0409. Min Act: -0.0003

Data Index: 184106 (C4 (Web Text))

Max Activating Token Index: 809

Text #10

Max Range: 0.0513. Min Range: -0.0513

Max Act: 0.0395. Min Act: -0.0003

Data Index: 579126 (C4 (Web Text))

Max Activating Token Index: 157

Text #11

Max Range: 0.0513. Min Range: -0.0513

Max Act: 0.0399. Min Act: -0.0003

Data Index: 106330 (C4 (Web Text))

Max Activating Token Index: 114

Text #12

Max Range: 0.0513. Min Range: -0.0513

Max Act: 0.0415. Min Act: -0.0003

Data Index: 972659 (C4 (Web Text))

Max Activating Token Index: 950

Text #13

Max Range: 0.0513. Min Range: -0.0513

Max Act: 0.0384. Min Act: -0.0003

Data Index: 302956 (C4 (Web Text))

Max Activating Token Index: 799

Text #14

Max Range: 0.0513. Min Range: -0.0513

Max Act: 0.0384. Min Act: -0.0003

Data Index: 933038 (C4 (Web Text))

Max Activating Token Index: 995

Text #15

Max Range: 0.0513. Min Range: -0.0513

Max Act: 0.0388. Min Act: -0.0003

Data Index: 637286 (C4 (Web Text))

Max Activating Token Index: 543

Text #16

Max Range: 0.0513. Min Range: -0.0513

Max Act: 0.0393. Min Act: -0.0003

Data Index: 1335329 (C4 (Web Text))

Max Activating Token Index: 939

Text #17

Max Range: 0.0513. Min Range: -0.0513

Max Act: 0.0412. Min Act: -0.0003

Data Index: 582981 (C4 (Web Text))

Max Activating Token Index: 357

Text #18

Max Range: 0.0513. Min Range: -0.0513

Max Act: 0.0384. Min Act: -0.0003

Data Index: 1163759 (C4 (Web Text))

Max Activating Token Index: 160

Text #19

Max Range: 0.0513. Min Range: -0.0513

Max Act: 0.0382. Min Act: -0.0003

Data Index: 67326 (C4 (Web Text))

Max Activating Token Index: 455