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

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

Neuron 1106 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: 0.0764. Min Range: -0.0764

Max Act: 0.0764. Min Act: -0.0006

Data Index: 1015272 (C4 (Web Text))

Max Activating Token Index: 540

Text #1

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0546. Min Act: -0.0006

Data Index: 184369 (C4 (Web Text))

Max Activating Token Index: 154

Text #2

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0562. Min Act: -0.0006

Data Index: 150598 (C4 (Web Text))

Max Activating Token Index: 275

Text #3

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0551. Min Act: -0.0006

Data Index: 1221902 (C4 (Web Text))

Max Activating Token Index: 604

Text #4

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0511. Min Act: -0.0006

Data Index: 110178 (C4 (Web Text))

Max Activating Token Index: 247

Text #5

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0510. Min Act: -0.0006

Data Index: 1132729 (C4 (Web Text))

Max Activating Token Index: 958

Text #6

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0515. Min Act: -0.0006

Data Index: 531307 (C4 (Web Text))

Max Activating Token Index: 868

Text #7

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0490. Min Act: -0.0006

Data Index: 1290370 (C4 (Web Text))

Max Activating Token Index: 327

Text #8

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0488. Min Act: -0.0006

Data Index: 291266 (C4 (Web Text))

Max Activating Token Index: 945

Text #9

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0505. Min Act: -0.0006

Data Index: 1204465 (C4 (Web Text))

Max Activating Token Index: 419

Text #10

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0485. Min Act: -0.0006

Data Index: 59367 (C4 (Web Text))

Max Activating Token Index: 733

Text #11

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0474. Min Act: -0.0006

Data Index: 505482 (C4 (Web Text))

Max Activating Token Index: 229

Text #12

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0494. Min Act: -0.0006

Data Index: 323243 (C4 (Web Text))

Max Activating Token Index: 944

Text #13

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0488. Min Act: -0.0006

Data Index: 480434 (C4 (Web Text))

Max Activating Token Index: 988

Text #14

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0478. Min Act: -0.0006

Data Index: 581212 (C4 (Web Text))

Max Activating Token Index: 1019

Text #15

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0487. Min Act: -0.0006

Data Index: 648724 (C4 (Web Text))

Max Activating Token Index: 690

Text #16

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0472. Min Act: -0.0006

Data Index: 1126805 (C4 (Web Text))

Max Activating Token Index: 1013

Text #17

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0464. Min Act: -0.0006

Data Index: 1210466 (C4 (Web Text))

Max Activating Token Index: 308

Text #18

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0462. Min Act: -0.0005

Data Index: 154105 (C4 (Web Text))

Max Activating Token Index: 981

Text #19

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0454. Min Act: -0.0006

Data Index: 691638 (C4 (Web Text))

Max Activating Token Index: 462