Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1382 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0485. Min Act: -0.0006

Data Index: 452352 (C4 (Web Text))

Max Activating Token Index: 251

Text #1

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0459. Min Act: -0.0006

Data Index: 1269978 (C4 (Web Text))

Max Activating Token Index: 338

Text #2

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0461. Min Act: -0.0006

Data Index: 771872 (C4 (Web Text))

Max Activating Token Index: 915

Text #3

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0467. Min Act: -0.0006

Data Index: 875639 (C4 (Web Text))

Max Activating Token Index: 879

Text #4

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0473. Min Act: -0.0006

Data Index: 771292 (C4 (Web Text))

Max Activating Token Index: 704

Text #5

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0432. Min Act: -0.0006

Data Index: 186987 (C4 (Web Text))

Max Activating Token Index: 983

Text #6

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0453. Min Act: -0.0006

Data Index: 1136923 (C4 (Web Text))

Max Activating Token Index: 357

Text #7

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0445. Min Act: -0.0006

Data Index: 834722 (C4 (Web Text))

Max Activating Token Index: 99

Text #8

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0454. Min Act: -0.0005

Data Index: 905221 (C4 (Web Text))

Max Activating Token Index: 797

Text #9

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0435. Min Act: -0.0006

Data Index: 53102 (C4 (Web Text))

Max Activating Token Index: 824

Text #10

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0418. Min Act: -0.0006

Data Index: 688903 (C4 (Web Text))

Max Activating Token Index: 955

Text #11

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0446. Min Act: -0.0006

Data Index: 390713 (C4 (Web Text))

Max Activating Token Index: 885

Text #12

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0419. Min Act: -0.0006

Data Index: 502297 (C4 (Web Text))

Max Activating Token Index: 909

Text #13

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0430. Min Act: -0.0006

Data Index: 1228257 (C4 (Web Text))

Max Activating Token Index: 877

Text #14

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0426. Min Act: -0.0006

Data Index: 883026 (C4 (Web Text))

Max Activating Token Index: 922

Text #15

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0428. Min Act: -0.0006

Data Index: 1097287 (C4 (Web Text))

Max Activating Token Index: 787

Text #16

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0429. Min Act: -0.0006

Data Index: 1038077 (C4 (Web Text))

Max Activating Token Index: 697

Text #17

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0416. Min Act: -0.0006

Data Index: 27114 (C4 (Web Text))

Max Activating Token Index: 12

Text #18

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0417. Min Act: -0.0006

Data Index: 685058 (C4 (Web Text))

Max Activating Token Index: 157

Text #19

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0434. Min Act: -0.0006

Data Index: 419498 (C4 (Web Text))

Max Activating Token Index: 409