Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 900 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.0803. Min Range: -1.0803

Max Act: 1.0803. Min Act: -0.0003

Data Index: 317088 (C4 (Web Text))

Max Activating Token Index: 711

Text #1

Max Range: 1.0803. Min Range: -1.0803

Max Act: 0.9833. Min Act: -0.0003

Data Index: 201369 (C4 (Web Text))

Max Activating Token Index: 235

Text #2

Max Range: 1.0803. Min Range: -1.0803

Max Act: 0.9068. Min Act: -0.0002

Data Index: 779338 (C4 (Web Text))

Max Activating Token Index: 174

Text #3

Max Range: 1.0803. Min Range: -1.0803

Max Act: 0.7602. Min Act: -0.0003

Data Index: 1286114 (C4 (Web Text))

Max Activating Token Index: 879

Text #4

Max Range: 1.0803. Min Range: -1.0803

Max Act: 0.7448. Min Act: -0.0003

Data Index: 322547 (C4 (Web Text))

Max Activating Token Index: 231

Text #5

Max Range: 1.0803. Min Range: -1.0803

Max Act: 0.7379. Min Act: -0.0003

Data Index: 1176702 (C4 (Web Text))

Max Activating Token Index: 104

Text #6

Max Range: 1.0803. Min Range: -1.0803

Max Act: 0.7343. Min Act: -0.0003

Data Index: 1316843 (C4 (Web Text))

Max Activating Token Index: 46

Text #7

Max Range: 1.0803. Min Range: -1.0803

Max Act: 0.7127. Min Act: -0.0003

Data Index: 416796 (C4 (Web Text))

Max Activating Token Index: 920

Text #8

Max Range: 1.0803. Min Range: -1.0803

Max Act: 0.7054. Min Act: -0.0003

Data Index: 21733 (C4 (Web Text))

Max Activating Token Index: 519

Text #9

Max Range: 1.0803. Min Range: -1.0803

Max Act: 0.6644. Min Act: -0.0003

Data Index: 545458 (C4 (Web Text))

Max Activating Token Index: 310

Text #10

Max Range: 1.0803. Min Range: -1.0803

Max Act: 0.6622. Min Act: -0.0003

Data Index: 128088 (C4 (Web Text))

Max Activating Token Index: 140

Text #11

Max Range: 1.0803. Min Range: -1.0803

Max Act: 0.6617. Min Act: -0.0003

Data Index: 498895 (C4 (Web Text))

Max Activating Token Index: 772

Text #12

Max Range: 1.0803. Min Range: -1.0803

Max Act: 0.6626. Min Act: -0.0003

Data Index: 503980 (C4 (Web Text))

Max Activating Token Index: 696

Text #13

Max Range: 1.0803. Min Range: -1.0803

Max Act: 0.6585. Min Act: -0.0003

Data Index: 750720 (C4 (Web Text))

Max Activating Token Index: 406

Text #14

Max Range: 1.0803. Min Range: -1.0803

Max Act: 0.6534. Min Act: -0.0003

Data Index: 1032343 (C4 (Web Text))

Max Activating Token Index: 150

Text #15

Max Range: 1.0803. Min Range: -1.0803

Max Act: 0.6519. Min Act: -0.0003

Data Index: 417069 (C4 (Web Text))

Max Activating Token Index: 277

Text #16

Max Range: 1.0803. Min Range: -1.0803

Max Act: 0.6496. Min Act: -0.0003

Data Index: 915829 (C4 (Web Text))

Max Activating Token Index: 184

Text #17

Max Range: 1.0803. Min Range: -1.0803

Max Act: 0.6437. Min Act: -0.0003

Data Index: 181678 (C4 (Web Text))

Max Activating Token Index: 167

Text #18

Max Range: 1.0803. Min Range: -1.0803

Max Act: 0.6315. Min Act: -0.0003

Data Index: 1266084 (C4 (Web Text))

Max Activating Token Index: 539

Text #19

Max Range: 1.0803. Min Range: -1.0803

Max Act: 0.6264. Min Act: -0.0003

Data Index: 495494 (C4 (Web Text))

Max Activating Token Index: 346