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

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

Neuron 3638 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5902. Min Range: -0.5902

Max Act: 0.5902. Min Act: -0.0000

Data Index: 510935 (C4 (Web Text))

Max Activating Token Index: 883

Text #1

Max Range: 0.5902. Min Range: -0.5902

Max Act: 0.5085. Min Act: 0.0000

Data Index: 982167 (C4 (Web Text))

Max Activating Token Index: 194

Text #2

Max Range: 0.5902. Min Range: -0.5902

Max Act: 0.4695. Min Act: -0.0000

Data Index: 1353018 (C4 (Web Text))

Max Activating Token Index: 792

Text #3

Max Range: 0.5902. Min Range: -0.5902

Max Act: 0.4811. Min Act: -0.0000

Data Index: 262146 (C4 (Web Text))

Max Activating Token Index: 390

Text #4

Max Range: 0.5902. Min Range: -0.5902

Max Act: 0.4488. Min Act: -0.0000

Data Index: 946325 (C4 (Web Text))

Max Activating Token Index: 641

Text #5

Max Range: 0.5902. Min Range: -0.5902

Max Act: 0.4553. Min Act: -0.0000

Data Index: 292895 (C4 (Web Text))

Max Activating Token Index: 166

Text #6

Max Range: 0.5902. Min Range: -0.5902

Max Act: 0.4552. Min Act: -0.0000

Data Index: 328064 (C4 (Web Text))

Max Activating Token Index: 343

Text #7

Max Range: 0.5902. Min Range: -0.5902

Max Act: 0.4365. Min Act: -0.0000

Data Index: 1217070 (C4 (Web Text))

Max Activating Token Index: 164

Text #8

Max Range: 0.5902. Min Range: -0.5902

Max Act: 0.4222. Min Act: -0.0000

Data Index: 1341452 (C4 (Web Text))

Max Activating Token Index: 180

Text #9

Max Range: 0.5902. Min Range: -0.5902

Max Act: 0.4455. Min Act: -0.0000

Data Index: 887809 (C4 (Web Text))

Max Activating Token Index: 135

Text #10

Max Range: 0.5902. Min Range: -0.5902

Max Act: 0.4463. Min Act: -0.0000

Data Index: 199464 (C4 (Web Text))

Max Activating Token Index: 987

Text #11

Max Range: 0.5902. Min Range: -0.5902

Max Act: 0.4337. Min Act: -0.0000

Data Index: 941929 (C4 (Web Text))

Max Activating Token Index: 822

Text #12

Max Range: 0.5902. Min Range: -0.5902

Max Act: 0.4291. Min Act: -0.0000

Data Index: 728631 (C4 (Web Text))

Max Activating Token Index: 681

Text #13

Max Range: 0.5902. Min Range: -0.5902

Max Act: 0.4233. Min Act: -0.0000

Data Index: 1026976 (C4 (Web Text))

Max Activating Token Index: 685

Text #14

Max Range: 0.5902. Min Range: -0.5902

Max Act: 0.4112. Min Act: -0.0000

Data Index: 597968 (C4 (Web Text))

Max Activating Token Index: 912

Text #15

Max Range: 0.5902. Min Range: -0.5902

Max Act: 0.4056. Min Act: -0.0000

Data Index: 687612 (C4 (Web Text))

Max Activating Token Index: 559

Text #16

Max Range: 0.5902. Min Range: -0.5902

Max Act: 0.4056. Min Act: -0.0000

Data Index: 723677 (C4 (Web Text))

Max Activating Token Index: 980

Text #17

Max Range: 0.5902. Min Range: -0.5902

Max Act: 0.4293. Min Act: -0.0000

Data Index: 656169 (C4 (Web Text))

Max Activating Token Index: 371

Text #18

Max Range: 0.5902. Min Range: -0.5902

Max Act: 0.4012. Min Act: 0.0000

Data Index: 229973 (C4 (Web Text))

Max Activating Token Index: 692

Text #19

Max Range: 0.5902. Min Range: -0.5902

Max Act: 0.4094. Min Act: -0.0000

Data Index: 480991 (C4 (Web Text))

Max Activating Token Index: 758