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

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

Neuron 93 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: 0.0211. Min Range: -0.0211

Max Act: 0.0211. Min Act: -0.0006

Data Index: 503053 (C4 (Web Text))

Max Activating Token Index: 493

Text #1

Max Range: 0.0211. Min Range: -0.0211

Max Act: 0.0200. Min Act: -0.0005

Data Index: 1264881 (C4 (Web Text))

Max Activating Token Index: 55

Text #2

Max Range: 0.0211. Min Range: -0.0211

Max Act: 0.0192. Min Act: -0.0006

Data Index: 646756 (C4 (Web Text))

Max Activating Token Index: 329

Text #3

Max Range: 0.0211. Min Range: -0.0211

Max Act: 0.0184. Min Act: -0.0006

Data Index: 969294 (C4 (Web Text))

Max Activating Token Index: 832

Text #4

Max Range: 0.0211. Min Range: -0.0211

Max Act: 0.0184. Min Act: -0.0006

Data Index: 7620 (C4 (Web Text))

Max Activating Token Index: 299

Text #5

Max Range: 0.0211. Min Range: -0.0211

Max Act: 0.0182. Min Act: -0.0006

Data Index: 146037 (C4 (Web Text))

Max Activating Token Index: 38

Text #6

Max Range: 0.0211. Min Range: -0.0211

Max Act: 0.0179. Min Act: -0.0006

Data Index: 470296 (C4 (Web Text))

Max Activating Token Index: 366

Text #7

Max Range: 0.0211. Min Range: -0.0211

Max Act: 0.0179. Min Act: -0.0006

Data Index: 234669 (C4 (Web Text))

Max Activating Token Index: 511

Text #8

Max Range: 0.0211. Min Range: -0.0211

Max Act: 0.0178. Min Act: -0.0006

Data Index: 819346 (C4 (Web Text))

Max Activating Token Index: 58

Text #9

Max Range: 0.0211. Min Range: -0.0211

Max Act: 0.0181. Min Act: -0.0006

Data Index: 50560 (C4 (Web Text))

Max Activating Token Index: 483

Text #10

Max Range: 0.0211. Min Range: -0.0211

Max Act: 0.0177. Min Act: -0.0006

Data Index: 604787 (C4 (Web Text))

Max Activating Token Index: 740

Text #11

Max Range: 0.0211. Min Range: -0.0211

Max Act: 0.0176. Min Act: -0.0006

Data Index: 539641 (C4 (Web Text))

Max Activating Token Index: 596

Text #12

Max Range: 0.0211. Min Range: -0.0211

Max Act: 0.0176. Min Act: -0.0006

Data Index: 415095 (C4 (Web Text))

Max Activating Token Index: 605

Text #13

Max Range: 0.0211. Min Range: -0.0211

Max Act: 0.0176. Min Act: -0.0006

Data Index: 1137290 (C4 (Web Text))

Max Activating Token Index: 665

Text #14

Max Range: 0.0211. Min Range: -0.0211

Max Act: 0.0170. Min Act: -0.0006

Data Index: 585337 (C4 (Web Text))

Max Activating Token Index: 355

Text #15

Max Range: 0.0211. Min Range: -0.0211

Max Act: 0.0171. Min Act: -0.0005

Data Index: 275201 (C4 (Web Text))

Max Activating Token Index: 708

Text #16

Max Range: 0.0211. Min Range: -0.0211

Max Act: 0.0174. Min Act: -0.0005

Data Index: 597914 (C4 (Web Text))

Max Activating Token Index: 496

Text #17

Max Range: 0.0211. Min Range: -0.0211

Max Act: 0.0172. Min Act: -0.0006

Data Index: 717715 (C4 (Web Text))

Max Activating Token Index: 278

Text #18

Max Range: 0.0211. Min Range: -0.0211

Max Act: 0.0167. Min Act: -0.0006

Data Index: 743433 (C4 (Web Text))

Max Activating Token Index: 836

Text #19

Max Range: 0.0211. Min Range: -0.0211

Max Act: 0.0174. Min Act: -0.0006

Data Index: 127039 (C4 (Web Text))

Max Activating Token Index: 74