Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1433 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.6131. Min Range: -0.6131

Max Act: 0.6131. Min Act: -0.0000

Data Index: 1545356 (Python Code)

Max Activating Token Index: 109

Text #1

Max Range: 0.6131. Min Range: -0.6131

Max Act: 0.5196. Min Act: -0.0000

Data Index: 1544561 (Python Code)

Max Activating Token Index: 72

Text #2

Max Range: 0.6131. Min Range: -0.6131

Max Act: 0.4684. Min Act: -0.0000

Data Index: 1568863 (Python Code)

Max Activating Token Index: 122

Text #3

Max Range: 0.6131. Min Range: -0.6131

Max Act: 0.3993. Min Act: -0.0000

Data Index: 1168701 (C4 (Web Text))

Max Activating Token Index: 804

Text #4

Max Range: 0.6131. Min Range: -0.6131

Max Act: 0.4015. Min Act: -0.0000

Data Index: 1528514 (Python Code)

Max Activating Token Index: 48

Text #5

Max Range: 0.6131. Min Range: -0.6131

Max Act: 0.3971. Min Act: -0.0000

Data Index: 399326 (C4 (Web Text))

Max Activating Token Index: 962

Text #6

Max Range: 0.6131. Min Range: -0.6131

Max Act: 0.3757. Min Act: -0.0000

Data Index: 1543573 (Python Code)

Max Activating Token Index: 402

Text #7

Max Range: 0.6131. Min Range: -0.6131

Max Act: 0.3376. Min Act: -0.0000

Data Index: 480635 (C4 (Web Text))

Max Activating Token Index: 871

Text #8

Max Range: 0.6131. Min Range: -0.6131

Max Act: 0.3357. Min Act: -0.0000

Data Index: 1338928 (C4 (Web Text))

Max Activating Token Index: 1019

Text #9

Max Range: 0.6131. Min Range: -0.6131

Max Act: 0.3409. Min Act: -0.0000

Data Index: 508059 (C4 (Web Text))

Max Activating Token Index: 978

Text #10

Max Range: 0.6131. Min Range: -0.6131

Max Act: 0.3555. Min Act: -0.0000

Data Index: 1630477 (Python Code)

Max Activating Token Index: 310

Text #11

Max Range: 0.6131. Min Range: -0.6131

Max Act: 0.3812. Min Act: -0.0000

Data Index: 1583079 (Python Code)

Max Activating Token Index: 565

Text #12

Max Range: 0.6131. Min Range: -0.6131

Max Act: 0.3192. Min Act: -0.0000

Data Index: 1301230 (C4 (Web Text))

Max Activating Token Index: 655

Text #13

Max Range: 0.6131. Min Range: -0.6131

Max Act: 0.3545. Min Act: -0.0000

Data Index: 1231264 (C4 (Web Text))

Max Activating Token Index: 910

Text #14

Max Range: 0.6131. Min Range: -0.6131

Max Act: 0.3696. Min Act: -0.0000

Data Index: 1125190 (C4 (Web Text))

Max Activating Token Index: 910

Text #15

Max Range: 0.6131. Min Range: -0.6131

Max Act: 0.3166. Min Act: -0.0000

Data Index: 1532032 (Python Code)

Max Activating Token Index: 206

Text #16

Max Range: 0.6131. Min Range: -0.6131

Max Act: 0.3505. Min Act: -0.0000

Data Index: 478092 (C4 (Web Text))

Max Activating Token Index: 983

Text #17

Max Range: 0.6131. Min Range: -0.6131

Max Act: 0.3404. Min Act: -0.0000

Data Index: 1537572 (Python Code)

Max Activating Token Index: 230

Text #18

Max Range: 0.6131. Min Range: -0.6131

Max Act: 0.3482. Min Act: -0.0000

Data Index: 1423398 (Python Code)

Max Activating Token Index: 488

Text #19

Max Range: 0.6131. Min Range: -0.6131

Max Act: 0.3512. Min Act: -0.0000

Data Index: 1229080 (C4 (Web Text))

Max Activating Token Index: 404