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

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

Neuron 3407 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: 0.2698. Min Range: -0.2698

Max Act: 0.2698. Min Act: -0.0000

Data Index: 805435 (C4 (Web Text))

Max Activating Token Index: 227

Text #1

Max Range: 0.2698. Min Range: -0.2698

Max Act: 0.2607. Min Act: -0.0000

Data Index: 1143372 (C4 (Web Text))

Max Activating Token Index: 94

Text #2

Max Range: 0.2698. Min Range: -0.2698

Max Act: 0.2442. Min Act: -0.0000

Data Index: 446174 (C4 (Web Text))

Max Activating Token Index: 992

Text #3

Max Range: 0.2698. Min Range: -0.2698

Max Act: 0.2372. Min Act: -0.0000

Data Index: 405491 (C4 (Web Text))

Max Activating Token Index: 660

Text #4

Max Range: 0.2698. Min Range: -0.2698

Max Act: 0.2349. Min Act: -0.0000

Data Index: 1063091 (C4 (Web Text))

Max Activating Token Index: 400

Text #5

Max Range: 0.2698. Min Range: -0.2698

Max Act: 0.2341. Min Act: -0.0000

Data Index: 548588 (C4 (Web Text))

Max Activating Token Index: 94

Text #6

Max Range: 0.2698. Min Range: -0.2698

Max Act: 0.2451. Min Act: -0.0000

Data Index: 360101 (C4 (Web Text))

Max Activating Token Index: 372

Text #7

Max Range: 0.2698. Min Range: -0.2698

Max Act: 0.2377. Min Act: -0.0000

Data Index: 587627 (C4 (Web Text))

Max Activating Token Index: 633

Text #8

Max Range: 0.2698. Min Range: -0.2698

Max Act: 0.2154. Min Act: -0.0000

Data Index: 1127773 (C4 (Web Text))

Max Activating Token Index: 303

Text #9

Max Range: 0.2698. Min Range: -0.2698

Max Act: 0.2222. Min Act: -0.0000

Data Index: 24265 (C4 (Web Text))

Max Activating Token Index: 452

Text #10

Max Range: 0.2698. Min Range: -0.2698

Max Act: 0.2210. Min Act: -0.0000

Data Index: 299229 (C4 (Web Text))

Max Activating Token Index: 357

Text #11

Max Range: 0.2698. Min Range: -0.2698

Max Act: 0.2120. Min Act: -0.0000

Data Index: 473175 (C4 (Web Text))

Max Activating Token Index: 924

Text #12

Max Range: 0.2698. Min Range: -0.2698

Max Act: 0.2119. Min Act: -0.0000

Data Index: 424587 (C4 (Web Text))

Max Activating Token Index: 134

Text #13

Max Range: 0.2698. Min Range: -0.2698

Max Act: 0.2108. Min Act: -0.0000

Data Index: 1049553 (C4 (Web Text))

Max Activating Token Index: 545

Text #14

Max Range: 0.2698. Min Range: -0.2698

Max Act: 0.1963. Min Act: -0.0000

Data Index: 768681 (C4 (Web Text))

Max Activating Token Index: 267

Text #15

Max Range: 0.2698. Min Range: -0.2698

Max Act: 0.2151. Min Act: -0.0000

Data Index: 1252331 (C4 (Web Text))

Max Activating Token Index: 272

Text #16

Max Range: 0.2698. Min Range: -0.2698

Max Act: 0.2294. Min Act: -0.0000

Data Index: 384046 (C4 (Web Text))

Max Activating Token Index: 213

Text #17

Max Range: 0.2698. Min Range: -0.2698

Max Act: 0.2174. Min Act: -0.0000

Data Index: 1022365 (C4 (Web Text))

Max Activating Token Index: 951

Text #18

Max Range: 0.2698. Min Range: -0.2698

Max Act: 0.2095. Min Act: -0.0000

Data Index: 300641 (C4 (Web Text))

Max Activating Token Index: 789

Text #19

Max Range: 0.2698. Min Range: -0.2698

Max Act: 0.2009. Min Act: -0.0000

Data Index: 781216 (C4 (Web Text))

Max Activating Token Index: 181