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

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

Neuron 1357 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: 0.0307. Min Range: -0.0307

Max Act: 0.0307. Min Act: -0.0006

Data Index: 1584879 (Python Code)

Max Activating Token Index: 98

Text #1

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0287. Min Act: -0.0006

Data Index: 920695 (C4 (Web Text))

Max Activating Token Index: 525

Text #2

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0284. Min Act: -0.0006

Data Index: 1541834 (Python Code)

Max Activating Token Index: 404

Text #3

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0269. Min Act: -0.0006

Data Index: 1601861 (Python Code)

Max Activating Token Index: 602

Text #4

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0265. Min Act: -0.0006

Data Index: 1400627 (Python Code)

Max Activating Token Index: 477

Text #5

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0257. Min Act: -0.0006

Data Index: 1458202 (Python Code)

Max Activating Token Index: 442

Text #6

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0258. Min Act: -0.0006

Data Index: 360130 (C4 (Web Text))

Max Activating Token Index: 56

Text #7

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0255. Min Act: -0.0006

Data Index: 1051400 (C4 (Web Text))

Max Activating Token Index: 856

Text #8

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0253. Min Act: -0.0006

Data Index: 650132 (C4 (Web Text))

Max Activating Token Index: 459

Text #9

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0257. Min Act: -0.0006

Data Index: 154483 (C4 (Web Text))

Max Activating Token Index: 531

Text #10

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0251. Min Act: -0.0006

Data Index: 1335779 (C4 (Web Text))

Max Activating Token Index: 969

Text #11

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0251. Min Act: -0.0006

Data Index: 997202 (C4 (Web Text))

Max Activating Token Index: 891

Text #12

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0248. Min Act: -0.0006

Data Index: 1554488 (Python Code)

Max Activating Token Index: 433

Text #13

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0243. Min Act: -0.0006

Data Index: 987035 (C4 (Web Text))

Max Activating Token Index: 866

Text #14

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0244. Min Act: -0.0006

Data Index: 315561 (C4 (Web Text))

Max Activating Token Index: 423

Text #15

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0232. Min Act: -0.0006

Data Index: 479407 (C4 (Web Text))

Max Activating Token Index: 819

Text #16

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0230. Min Act: -0.0006

Data Index: 1109084 (C4 (Web Text))

Max Activating Token Index: 220

Text #17

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0235. Min Act: -0.0006

Data Index: 1130484 (C4 (Web Text))

Max Activating Token Index: 390

Text #18

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0229. Min Act: -0.0006

Data Index: 1585922 (Python Code)

Max Activating Token Index: 966

Text #19

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0234. Min Act: -0.0006

Data Index: 177493 (C4 (Web Text))

Max Activating Token Index: 780