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

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

Neuron 521 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5628. Min Range: -0.5628

Max Act: 0.5628. Min Act: -0.0000

Data Index: 511142 (C4 (Web Text))

Max Activating Token Index: 907

Text #1

Max Range: 0.5628. Min Range: -0.5628

Max Act: 0.5068. Min Act: 0.0000

Data Index: 1181238 (C4 (Web Text))

Max Activating Token Index: 430

Text #2

Max Range: 0.5628. Min Range: -0.5628

Max Act: 0.4748. Min Act: -0.0000

Data Index: 116861 (C4 (Web Text))

Max Activating Token Index: 276

Text #3

Max Range: 0.5628. Min Range: -0.5628

Max Act: 0.4619. Min Act: -0.0000

Data Index: 733913 (C4 (Web Text))

Max Activating Token Index: 202

Text #4

Max Range: 0.5628. Min Range: -0.5628

Max Act: 0.4228. Min Act: -0.0000

Data Index: 1183998 (C4 (Web Text))

Max Activating Token Index: 418

Text #5

Max Range: 0.5628. Min Range: -0.5628

Max Act: 0.4307. Min Act: -0.0000

Data Index: 154788 (C4 (Web Text))

Max Activating Token Index: 426

Text #6

Max Range: 0.5628. Min Range: -0.5628

Max Act: 0.4304. Min Act: -0.0000

Data Index: 369779 (C4 (Web Text))

Max Activating Token Index: 1010

Text #7

Max Range: 0.5628. Min Range: -0.5628

Max Act: 0.4220. Min Act: -0.0000

Data Index: 522296 (C4 (Web Text))

Max Activating Token Index: 577

Text #8

Max Range: 0.5628. Min Range: -0.5628

Max Act: 0.4200. Min Act: -0.0000

Data Index: 97572 (C4 (Web Text))

Max Activating Token Index: 687

Text #9

Max Range: 0.5628. Min Range: -0.5628

Max Act: 0.3893. Min Act: -0.0000

Data Index: 1048903 (C4 (Web Text))

Max Activating Token Index: 686

Text #10

Max Range: 0.5628. Min Range: -0.5628

Max Act: 0.3715. Min Act: -0.0000

Data Index: 1222689 (C4 (Web Text))

Max Activating Token Index: 163

Text #11

Max Range: 0.5628. Min Range: -0.5628

Max Act: 0.3770. Min Act: -0.0000

Data Index: 1314812 (C4 (Web Text))

Max Activating Token Index: 228

Text #12

Max Range: 0.5628. Min Range: -0.5628

Max Act: 0.3493. Min Act: -0.0000

Data Index: 515596 (C4 (Web Text))

Max Activating Token Index: 706

Text #13

Max Range: 0.5628. Min Range: -0.5628

Max Act: 0.3575. Min Act: -0.0000

Data Index: 1047157 (C4 (Web Text))

Max Activating Token Index: 103

Text #14

Max Range: 0.5628. Min Range: -0.5628

Max Act: 0.3355. Min Act: 0.0000

Data Index: 916589 (C4 (Web Text))

Max Activating Token Index: 620

Text #15

Max Range: 0.5628. Min Range: -0.5628

Max Act: 0.3318. Min Act: -0.0000

Data Index: 685708 (C4 (Web Text))

Max Activating Token Index: 994

Text #16

Max Range: 0.5628. Min Range: -0.5628

Max Act: 0.3343. Min Act: -0.0000

Data Index: 218951 (C4 (Web Text))

Max Activating Token Index: 61

Text #17

Max Range: 0.5628. Min Range: -0.5628

Max Act: 0.3119. Min Act: -0.0000

Data Index: 569827 (C4 (Web Text))

Max Activating Token Index: 958

Text #18

Max Range: 0.5628. Min Range: -0.5628

Max Act: 0.3205. Min Act: -0.0000

Data Index: 147268 (C4 (Web Text))

Max Activating Token Index: 422

Text #19

Max Range: 0.5628. Min Range: -0.5628

Max Act: 0.3150. Min Act: -0.0000

Data Index: 1009214 (C4 (Web Text))

Max Activating Token Index: 216