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

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

Neuron 3994 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: 0.6513. Min Range: -0.6513

Max Act: 0.6401. Min Act: -0.0000

Data Index: 1300116 (C4 (Web Text))

Max Activating Token Index: 117

Text #1

Max Range: 0.6513. Min Range: -0.6513

Max Act: 0.6513. Min Act: -0.0000

Data Index: 703707 (C4 (Web Text))

Max Activating Token Index: 139

Text #2

Max Range: 0.6513. Min Range: -0.6513

Max Act: 0.5771. Min Act: -0.0000

Data Index: 1292903 (C4 (Web Text))

Max Activating Token Index: 948

Text #3

Max Range: 0.6513. Min Range: -0.6513

Max Act: 0.5887. Min Act: -0.0000

Data Index: 273281 (C4 (Web Text))

Max Activating Token Index: 121

Text #4

Max Range: 0.6513. Min Range: -0.6513

Max Act: 0.5955. Min Act: -0.0000

Data Index: 723977 (C4 (Web Text))

Max Activating Token Index: 622

Text #5

Max Range: 0.6513. Min Range: -0.6513

Max Act: 0.6151. Min Act: -0.0000

Data Index: 1441 (C4 (Web Text))

Max Activating Token Index: 189

Text #6

Max Range: 0.6513. Min Range: -0.6513

Max Act: 0.6187. Min Act: -0.0000

Data Index: 754104 (C4 (Web Text))

Max Activating Token Index: 206

Text #7

Max Range: 0.6513. Min Range: -0.6513

Max Act: 0.5961. Min Act: -0.0000

Data Index: 583405 (C4 (Web Text))

Max Activating Token Index: 412

Text #8

Max Range: 0.6513. Min Range: -0.6513

Max Act: 0.5741. Min Act: -0.0000

Data Index: 934415 (C4 (Web Text))

Max Activating Token Index: 232

Text #9

Max Range: 0.6513. Min Range: -0.6513

Max Act: 0.5726. Min Act: -0.0000

Data Index: 670768 (C4 (Web Text))

Max Activating Token Index: 564

Text #10

Max Range: 0.6513. Min Range: -0.6513

Max Act: 0.5374. Min Act: -0.0000

Data Index: 16692 (C4 (Web Text))

Max Activating Token Index: 225

Text #11

Max Range: 0.6513. Min Range: -0.6513

Max Act: 0.5476. Min Act: -0.0000

Data Index: 264224 (C4 (Web Text))

Max Activating Token Index: 805

Text #12

Max Range: 0.6513. Min Range: -0.6513

Max Act: 0.5604. Min Act: -0.0000

Data Index: 368071 (C4 (Web Text))

Max Activating Token Index: 56

Text #13

Max Range: 0.6513. Min Range: -0.6513

Max Act: 0.5547. Min Act: -0.0000

Data Index: 196857 (C4 (Web Text))

Max Activating Token Index: 522

Text #14

Max Range: 0.6513. Min Range: -0.6513

Max Act: 0.5379. Min Act: -0.0000

Data Index: 225831 (C4 (Web Text))

Max Activating Token Index: 61

Text #15

Max Range: 0.6513. Min Range: -0.6513

Max Act: 0.5152. Min Act: -0.0000

Data Index: 254001 (C4 (Web Text))

Max Activating Token Index: 475

Text #16

Max Range: 0.6513. Min Range: -0.6513

Max Act: 0.5100. Min Act: -0.0000

Data Index: 335189 (C4 (Web Text))

Max Activating Token Index: 889

Text #17

Max Range: 0.6513. Min Range: -0.6513

Max Act: 0.5073. Min Act: -0.0000

Data Index: 350406 (C4 (Web Text))

Max Activating Token Index: 203

Text #18

Max Range: 0.6513. Min Range: -0.6513

Max Act: 0.5332. Min Act: -0.0000

Data Index: 1240950 (C4 (Web Text))

Max Activating Token Index: 712

Text #19

Max Range: 0.6513. Min Range: -0.6513

Max Act: 0.5251. Min Act: -0.0000

Data Index: 436913 (C4 (Web Text))

Max Activating Token Index: 41