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

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

Neuron 1458 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: 0.0323. Min Range: -0.0323

Max Act: 0.0308. Min Act: -0.0006

Data Index: 84028 (C4 (Web Text))

Max Activating Token Index: 774

Text #1

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0309. Min Act: -0.0006

Data Index: 95433 (C4 (Web Text))

Max Activating Token Index: 85

Text #2

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0323. Min Act: -0.0006

Data Index: 651684 (C4 (Web Text))

Max Activating Token Index: 852

Text #3

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0285. Min Act: -0.0006

Data Index: 123767 (C4 (Web Text))

Max Activating Token Index: 750

Text #4

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0295. Min Act: -0.0006

Data Index: 894099 (C4 (Web Text))

Max Activating Token Index: 275

Text #5

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0269. Min Act: -0.0006

Data Index: 484294 (C4 (Web Text))

Max Activating Token Index: 683

Text #6

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0276. Min Act: -0.0005

Data Index: 737337 (C4 (Web Text))

Max Activating Token Index: 776

Text #7

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0256. Min Act: -0.0006

Data Index: 890606 (C4 (Web Text))

Max Activating Token Index: 197

Text #8

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0271. Min Act: -0.0006

Data Index: 713504 (C4 (Web Text))

Max Activating Token Index: 71

Text #9

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0273. Min Act: -0.0006

Data Index: 1129306 (C4 (Web Text))

Max Activating Token Index: 1018

Text #10

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0271. Min Act: -0.0006

Data Index: 454905 (C4 (Web Text))

Max Activating Token Index: 97

Text #11

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0270. Min Act: -0.0006

Data Index: 683242 (C4 (Web Text))

Max Activating Token Index: 442

Text #12

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0276. Min Act: -0.0006

Data Index: 82196 (C4 (Web Text))

Max Activating Token Index: 581

Text #13

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0263. Min Act: -0.0006

Data Index: 573717 (C4 (Web Text))

Max Activating Token Index: 485

Text #14

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0267. Min Act: -0.0006

Data Index: 602566 (C4 (Web Text))

Max Activating Token Index: 119

Text #15

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0273. Min Act: -0.0006

Data Index: 145898 (C4 (Web Text))

Max Activating Token Index: 337

Text #16

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0272. Min Act: -0.0006

Data Index: 16999 (C4 (Web Text))

Max Activating Token Index: 161

Text #17

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0278. Min Act: -0.0006

Data Index: 141744 (C4 (Web Text))

Max Activating Token Index: 330

Text #18

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0265. Min Act: -0.0006

Data Index: 1154368 (C4 (Web Text))

Max Activating Token Index: 546

Text #19

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0265. Min Act: -0.0006

Data Index: 151284 (C4 (Web Text))

Max Activating Token Index: 241