Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4604 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 5.2151. Min Range: -5.2151

Max Act: 5.2151. Min Act: -0.0000

Data Index: 1023651 (C4 (Web Text))

Max Activating Token Index: 967

Text #1

Max Range: 5.2151. Min Range: -5.2151

Max Act: 5.1820. Min Act: -0.0000

Data Index: 74096 (C4 (Web Text))

Max Activating Token Index: 248

Text #2

Max Range: 5.2151. Min Range: -5.2151

Max Act: 5.1298. Min Act: -0.0000

Data Index: 526675 (C4 (Web Text))

Max Activating Token Index: 280

Text #3

Max Range: 5.2151. Min Range: -5.2151

Max Act: 4.8945. Min Act: -0.0000

Data Index: 32110 (C4 (Web Text))

Max Activating Token Index: 636

Text #4

Max Range: 5.2151. Min Range: -5.2151

Max Act: 4.8177. Min Act: -0.0000

Data Index: 489683 (C4 (Web Text))

Max Activating Token Index: 405

Text #5

Max Range: 5.2151. Min Range: -5.2151

Max Act: 4.5235. Min Act: -0.0000

Data Index: 828912 (C4 (Web Text))

Max Activating Token Index: 304

Text #6

Max Range: 5.2151. Min Range: -5.2151

Max Act: 5.0114. Min Act: -0.0000

Data Index: 994533 (C4 (Web Text))

Max Activating Token Index: 707

Text #7

Max Range: 5.2151. Min Range: -5.2151

Max Act: 4.6518. Min Act: -0.0000

Data Index: 849172 (C4 (Web Text))

Max Activating Token Index: 874

Text #8

Max Range: 5.2151. Min Range: -5.2151

Max Act: 4.7542. Min Act: -0.0000

Data Index: 709305 (C4 (Web Text))

Max Activating Token Index: 502

Text #9

Max Range: 5.2151. Min Range: -5.2151

Max Act: 4.5508. Min Act: -0.0000

Data Index: 104248 (C4 (Web Text))

Max Activating Token Index: 279

Text #10

Max Range: 5.2151. Min Range: -5.2151

Max Act: 4.7222. Min Act: -0.0000

Data Index: 340495 (C4 (Web Text))

Max Activating Token Index: 535

Text #11

Max Range: 5.2151. Min Range: -5.2151

Max Act: 4.6792. Min Act: -0.0000

Data Index: 770490 (C4 (Web Text))

Max Activating Token Index: 141

Text #12

Max Range: 5.2151. Min Range: -5.2151

Max Act: 4.2694. Min Act: -0.0000

Data Index: 655041 (C4 (Web Text))

Max Activating Token Index: 238

Text #13

Max Range: 5.2151. Min Range: -5.2151

Max Act: 4.7557. Min Act: -0.0000

Data Index: 268052 (C4 (Web Text))

Max Activating Token Index: 39

Text #14

Max Range: 5.2151. Min Range: -5.2151

Max Act: 4.3657. Min Act: -0.0000

Data Index: 927192 (C4 (Web Text))

Max Activating Token Index: 227

Text #15

Max Range: 5.2151. Min Range: -5.2151

Max Act: 4.5227. Min Act: -0.0000

Data Index: 996357 (C4 (Web Text))

Max Activating Token Index: 152

Text #16

Max Range: 5.2151. Min Range: -5.2151

Max Act: 4.6553. Min Act: -0.0000

Data Index: 1228878 (C4 (Web Text))

Max Activating Token Index: 347

Text #17

Max Range: 5.2151. Min Range: -5.2151

Max Act: 4.4971. Min Act: -0.0000

Data Index: 277904 (C4 (Web Text))

Max Activating Token Index: 239

Text #18

Max Range: 5.2151. Min Range: -5.2151

Max Act: 4.3210. Min Act: -0.0000

Data Index: 371171 (C4 (Web Text))

Max Activating Token Index: 506

Text #19

Max Range: 5.2151. Min Range: -5.2151

Max Act: 4.4661. Min Act: -0.0000

Data Index: 372234 (C4 (Web Text))

Max Activating Token Index: 19