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

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

Neuron 581 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: 982759 (C4 (Web Text))

Max Activating Token Index: 448

Text #1

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0264. Min Act: -0.0006

Data Index: 691982 (C4 (Web Text))

Max Activating Token Index: 119

Text #2

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0254. Min Act: -0.0006

Data Index: 909804 (C4 (Web Text))

Max Activating Token Index: 521

Text #3

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0253. Min Act: -0.0006

Data Index: 873402 (C4 (Web Text))

Max Activating Token Index: 457

Text #4

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0246. Min Act: -0.0006

Data Index: 950922 (C4 (Web Text))

Max Activating Token Index: 128

Text #5

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0244. Min Act: -0.0006

Data Index: 324014 (C4 (Web Text))

Max Activating Token Index: 691

Text #6

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0236. Min Act: -0.0006

Data Index: 1112890 (C4 (Web Text))

Max Activating Token Index: 654

Text #7

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0254. Min Act: -0.0006

Data Index: 227802 (C4 (Web Text))

Max Activating Token Index: 418

Text #8

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0244. Min Act: -0.0006

Data Index: 1077545 (C4 (Web Text))

Max Activating Token Index: 355

Text #9

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0254. Min Act: -0.0006

Data Index: 835175 (C4 (Web Text))

Max Activating Token Index: 715

Text #10

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0240. Min Act: -0.0006

Data Index: 236711 (C4 (Web Text))

Max Activating Token Index: 485

Text #11

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0238. Min Act: -0.0006

Data Index: 443754 (C4 (Web Text))

Max Activating Token Index: 535

Text #12

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0227. Min Act: -0.0006

Data Index: 1054300 (C4 (Web Text))

Max Activating Token Index: 456

Text #13

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0231. Min Act: -0.0006

Data Index: 304458 (C4 (Web Text))

Max Activating Token Index: 624

Text #14

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0236. Min Act: -0.0006

Data Index: 1317619 (C4 (Web Text))

Max Activating Token Index: 728

Text #15

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0237. Min Act: -0.0006

Data Index: 1151927 (C4 (Web Text))

Max Activating Token Index: 198

Text #16

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0229. Min Act: -0.0006

Data Index: 968947 (C4 (Web Text))

Max Activating Token Index: 335

Text #17

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0232. Min Act: -0.0006

Data Index: 1275626 (C4 (Web Text))

Max Activating Token Index: 911

Text #18

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0229. Min Act: -0.0006

Data Index: 487635 (C4 (Web Text))

Max Activating Token Index: 203

Text #19

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0234. Min Act: -0.0006

Data Index: 94227 (C4 (Web Text))

Max Activating Token Index: 852