Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 421 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0725. Min Act: -0.0006

Data Index: 837844 (C4 (Web Text))

Max Activating Token Index: 634

Text #1

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0561. Min Act: -0.0006

Data Index: 1038265 (C4 (Web Text))

Max Activating Token Index: 792

Text #2

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0545. Min Act: -0.0006

Data Index: 925086 (C4 (Web Text))

Max Activating Token Index: 592

Text #3

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0547. Min Act: -0.0006

Data Index: 1155443 (C4 (Web Text))

Max Activating Token Index: 439

Text #4

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0493. Min Act: -0.0006

Data Index: 515612 (C4 (Web Text))

Max Activating Token Index: 886

Text #5

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0523. Min Act: -0.0006

Data Index: 1353298 (C4 (Web Text))

Max Activating Token Index: 154

Text #6

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0510. Min Act: -0.0006

Data Index: 871748 (C4 (Web Text))

Max Activating Token Index: 947

Text #7

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0528. Min Act: -0.0006

Data Index: 663739 (C4 (Web Text))

Max Activating Token Index: 758

Text #8

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0507. Min Act: -0.0006

Data Index: 83052 (C4 (Web Text))

Max Activating Token Index: 711

Text #9

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0478. Min Act: -0.0006

Data Index: 1251460 (C4 (Web Text))

Max Activating Token Index: 594

Text #10

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0506. Min Act: -0.0006

Data Index: 369963 (C4 (Web Text))

Max Activating Token Index: 394

Text #11

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0399. Min Act: -0.0006

Data Index: 1082680 (C4 (Web Text))

Max Activating Token Index: 660

Text #12

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0515. Min Act: -0.0006

Data Index: 48279 (C4 (Web Text))

Max Activating Token Index: 158

Text #13

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0514. Min Act: -0.0006

Data Index: 471028 (C4 (Web Text))

Max Activating Token Index: 571

Text #14

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0468. Min Act: -0.0006

Data Index: 253438 (C4 (Web Text))

Max Activating Token Index: 1006

Text #15

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0491. Min Act: -0.0006

Data Index: 229012 (C4 (Web Text))

Max Activating Token Index: 655

Text #16

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0472. Min Act: -0.0006

Data Index: 1005067 (C4 (Web Text))

Max Activating Token Index: 133

Text #17

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0489. Min Act: -0.0006

Data Index: 437286 (C4 (Web Text))

Max Activating Token Index: 246

Text #18

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0542. Min Act: -0.0006

Data Index: 1190911 (C4 (Web Text))

Max Activating Token Index: 629

Text #19

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0451. Min Act: -0.0006

Data Index: 4133 (C4 (Web Text))

Max Activating Token Index: 662