Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 630 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0369. Min Range: -0.0369

Max Act: 0.0235. Min Act: -0.0006

Data Index: 1155409 (C4 (Web Text))

Max Activating Token Index: 476

Text #1

Max Range: 0.0369. Min Range: -0.0369

Max Act: 0.0249. Min Act: -0.0006

Data Index: 1086211 (C4 (Web Text))

Max Activating Token Index: 720

Text #2

Max Range: 0.0369. Min Range: -0.0369

Max Act: 0.0369. Min Act: -0.0006

Data Index: 1294151 (C4 (Web Text))

Max Activating Token Index: 489

Text #3

Max Range: 0.0369. Min Range: -0.0369

Max Act: 0.0353. Min Act: -0.0006

Data Index: 190846 (C4 (Web Text))

Max Activating Token Index: 1012

Text #4

Max Range: 0.0369. Min Range: -0.0369

Max Act: 0.0309. Min Act: -0.0006

Data Index: 226430 (C4 (Web Text))

Max Activating Token Index: 666

Text #5

Max Range: 0.0369. Min Range: -0.0369

Max Act: 0.0323. Min Act: -0.0006

Data Index: 329240 (C4 (Web Text))

Max Activating Token Index: 197

Text #6

Max Range: 0.0369. Min Range: -0.0369

Max Act: 0.0300. Min Act: -0.0006

Data Index: 978571 (C4 (Web Text))

Max Activating Token Index: 23

Text #7

Max Range: 0.0369. Min Range: -0.0369

Max Act: 0.0307. Min Act: -0.0006

Data Index: 837103 (C4 (Web Text))

Max Activating Token Index: 234

Text #8

Max Range: 0.0369. Min Range: -0.0369

Max Act: 0.0299. Min Act: -0.0006

Data Index: 430035 (C4 (Web Text))

Max Activating Token Index: 107

Text #9

Max Range: 0.0369. Min Range: -0.0369

Max Act: 0.0233. Min Act: -0.0006

Data Index: 1197931 (C4 (Web Text))

Max Activating Token Index: 152

Text #10

Max Range: 0.0369. Min Range: -0.0369

Max Act: 0.0305. Min Act: -0.0006

Data Index: 607058 (C4 (Web Text))

Max Activating Token Index: 171

Text #11

Max Range: 0.0369. Min Range: -0.0369

Max Act: 0.0278. Min Act: -0.0006

Data Index: 1191044 (C4 (Web Text))

Max Activating Token Index: 389

Text #12

Max Range: 0.0369. Min Range: -0.0369

Max Act: 0.0331. Min Act: -0.0006

Data Index: 22365 (C4 (Web Text))

Max Activating Token Index: 476

Text #13

Max Range: 0.0369. Min Range: -0.0369

Max Act: 0.0268. Min Act: -0.0006

Data Index: 914866 (C4 (Web Text))

Max Activating Token Index: 786

Text #14

Max Range: 0.0369. Min Range: -0.0369

Max Act: 0.0267. Min Act: -0.0006

Data Index: 389964 (C4 (Web Text))

Max Activating Token Index: 198

Text #15

Max Range: 0.0369. Min Range: -0.0369

Max Act: 0.0261. Min Act: -0.0006

Data Index: 980548 (C4 (Web Text))

Max Activating Token Index: 166

Text #16

Max Range: 0.0369. Min Range: -0.0369

Max Act: 0.0278. Min Act: -0.0006

Data Index: 834012 (C4 (Web Text))

Max Activating Token Index: 586

Text #17

Max Range: 0.0369. Min Range: -0.0369

Max Act: 0.0260. Min Act: -0.0006

Data Index: 603173 (C4 (Web Text))

Max Activating Token Index: 163

Text #18

Max Range: 0.0369. Min Range: -0.0369

Max Act: 0.0278. Min Act: -0.0006

Data Index: 443625 (C4 (Web Text))

Max Activating Token Index: 803

Text #19

Max Range: 0.0369. Min Range: -0.0369

Max Act: 0.0271. Min Act: -0.0006

Data Index: 139651 (C4 (Web Text))

Max Activating Token Index: 173