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

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

Neuron 2736 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: 2.6559. Min Range: -2.6559

Max Act: 2.6559. Min Act: -0.0000

Data Index: 676660 (C4 (Web Text))

Max Activating Token Index: 89

Text #1

Max Range: 2.6559. Min Range: -2.6559

Max Act: 2.5162. Min Act: -0.0000

Data Index: 300262 (C4 (Web Text))

Max Activating Token Index: 244

Text #2

Max Range: 2.6559. Min Range: -2.6559

Max Act: 2.4266. Min Act: -0.0000

Data Index: 1171176 (C4 (Web Text))

Max Activating Token Index: 1000

Text #3

Max Range: 2.6559. Min Range: -2.6559

Max Act: 2.3596. Min Act: -0.0000

Data Index: 1154546 (C4 (Web Text))

Max Activating Token Index: 170

Text #4

Max Range: 2.6559. Min Range: -2.6559

Max Act: 2.4782. Min Act: -0.0000

Data Index: 734007 (C4 (Web Text))

Max Activating Token Index: 650

Text #5

Max Range: 2.6559. Min Range: -2.6559

Max Act: 2.4532. Min Act: -0.0000

Data Index: 945057 (C4 (Web Text))

Max Activating Token Index: 197

Text #6

Max Range: 2.6559. Min Range: -2.6559

Max Act: 2.4293. Min Act: -0.0000

Data Index: 601630 (C4 (Web Text))

Max Activating Token Index: 137

Text #7

Max Range: 2.6559. Min Range: -2.6559

Max Act: 2.2074. Min Act: -0.0000

Data Index: 473408 (C4 (Web Text))

Max Activating Token Index: 229

Text #8

Max Range: 2.6559. Min Range: -2.6559

Max Act: 2.1264. Min Act: -0.0000

Data Index: 623337 (C4 (Web Text))

Max Activating Token Index: 413

Text #9

Max Range: 2.6559. Min Range: -2.6559

Max Act: 2.0300. Min Act: -0.0000

Data Index: 345976 (C4 (Web Text))

Max Activating Token Index: 313

Text #10

Max Range: 2.6559. Min Range: -2.6559

Max Act: 2.0356. Min Act: -0.0000

Data Index: 1351468 (C4 (Web Text))

Max Activating Token Index: 164

Text #11

Max Range: 2.6559. Min Range: -2.6559

Max Act: 2.0244. Min Act: -0.0000

Data Index: 26314 (C4 (Web Text))

Max Activating Token Index: 788

Text #12

Max Range: 2.6559. Min Range: -2.6559

Max Act: 1.9140. Min Act: -0.0000

Data Index: 379134 (C4 (Web Text))

Max Activating Token Index: 521

Text #13

Max Range: 2.6559. Min Range: -2.6559

Max Act: 2.0133. Min Act: -0.0000

Data Index: 796014 (C4 (Web Text))

Max Activating Token Index: 468

Text #14

Max Range: 2.6559. Min Range: -2.6559

Max Act: 1.9130. Min Act: -0.0000

Data Index: 390548 (C4 (Web Text))

Max Activating Token Index: 308

Text #15

Max Range: 2.6559. Min Range: -2.6559

Max Act: 2.0607. Min Act: -0.0000

Data Index: 116672 (C4 (Web Text))

Max Activating Token Index: 307

Text #16

Max Range: 2.6559. Min Range: -2.6559

Max Act: 1.8172. Min Act: -0.0000

Data Index: 743460 (C4 (Web Text))

Max Activating Token Index: 338

Text #17

Max Range: 2.6559. Min Range: -2.6559

Max Act: 1.8064. Min Act: -0.0000

Data Index: 703828 (C4 (Web Text))

Max Activating Token Index: 799

Text #18

Max Range: 2.6559. Min Range: -2.6559

Max Act: 2.0067. Min Act: -0.0000

Data Index: 321871 (C4 (Web Text))

Max Activating Token Index: 136

Text #19

Max Range: 2.6559. Min Range: -2.6559

Max Act: 1.9919. Min Act: -0.0000

Data Index: 951999 (C4 (Web Text))

Max Activating Token Index: 1006