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

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

Neuron 581 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6255. Min Range: -0.6255

Max Act: 0.6194. Min Act: -0.0000

Data Index: 648196 (C4 (Web Text))

Max Activating Token Index: 208

Text #1

Max Range: 0.6255. Min Range: -0.6255

Max Act: 0.6221. Min Act: -0.0000

Data Index: 859243 (C4 (Web Text))

Max Activating Token Index: 209

Text #2

Max Range: 0.6255. Min Range: -0.6255

Max Act: 0.6189. Min Act: -0.0000

Data Index: 959153 (C4 (Web Text))

Max Activating Token Index: 568

Text #3

Max Range: 0.6255. Min Range: -0.6255

Max Act: 0.6132. Min Act: -0.0000

Data Index: 308601 (C4 (Web Text))

Max Activating Token Index: 430

Text #4

Max Range: 0.6255. Min Range: -0.6255

Max Act: 0.5404. Min Act: -0.0000

Data Index: 545465 (C4 (Web Text))

Max Activating Token Index: 788

Text #5

Max Range: 0.6255. Min Range: -0.6255

Max Act: 0.5643. Min Act: -0.0000

Data Index: 366583 (C4 (Web Text))

Max Activating Token Index: 314

Text #6

Max Range: 0.6255. Min Range: -0.6255

Max Act: 0.6255. Min Act: -0.0000

Data Index: 402874 (C4 (Web Text))

Max Activating Token Index: 870

Text #7

Max Range: 0.6255. Min Range: -0.6255

Max Act: 0.5235. Min Act: -0.0000

Data Index: 126644 (C4 (Web Text))

Max Activating Token Index: 242

Text #8

Max Range: 0.6255. Min Range: -0.6255

Max Act: 0.5393. Min Act: -0.0000

Data Index: 309820 (C4 (Web Text))

Max Activating Token Index: 471

Text #9

Max Range: 0.6255. Min Range: -0.6255

Max Act: 0.5868. Min Act: -0.0000

Data Index: 540802 (C4 (Web Text))

Max Activating Token Index: 261

Text #10

Max Range: 0.6255. Min Range: -0.6255

Max Act: 0.6214. Min Act: -0.0000

Data Index: 1116471 (C4 (Web Text))

Max Activating Token Index: 150

Text #11

Max Range: 0.6255. Min Range: -0.6255

Max Act: 0.5997. Min Act: -0.0000

Data Index: 1000059 (C4 (Web Text))

Max Activating Token Index: 325

Text #12

Max Range: 0.6255. Min Range: -0.6255

Max Act: 0.5693. Min Act: -0.0000

Data Index: 1196638 (C4 (Web Text))

Max Activating Token Index: 126

Text #13

Max Range: 0.6255. Min Range: -0.6255

Max Act: 0.5725. Min Act: -0.0000

Data Index: 1179432 (C4 (Web Text))

Max Activating Token Index: 950

Text #14

Max Range: 0.6255. Min Range: -0.6255

Max Act: 0.5305. Min Act: -0.0000

Data Index: 948127 (C4 (Web Text))

Max Activating Token Index: 239

Text #15

Max Range: 0.6255. Min Range: -0.6255

Max Act: 0.6239. Min Act: -0.0000

Data Index: 1243816 (C4 (Web Text))

Max Activating Token Index: 301

Text #16

Max Range: 0.6255. Min Range: -0.6255

Max Act: 0.5794. Min Act: -0.0000

Data Index: 5036 (C4 (Web Text))

Max Activating Token Index: 433

Text #17

Max Range: 0.6255. Min Range: -0.6255

Max Act: 0.5361. Min Act: -0.0000

Data Index: 1321721 (C4 (Web Text))

Max Activating Token Index: 542

Text #18

Max Range: 0.6255. Min Range: -0.6255

Max Act: 0.5451. Min Act: -0.0000

Data Index: 1123132 (C4 (Web Text))

Max Activating Token Index: 129

Text #19

Max Range: 0.6255. Min Range: -0.6255

Max Act: 0.6047. Min Act: -0.0000

Data Index: 664659 (C4 (Web Text))

Max Activating Token Index: 84