Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2953 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.6564. Min Range: -2.6564

Max Act: 2.6564. Min Act: -0.0000

Data Index: 1235738 (C4 (Web Text))

Max Activating Token Index: 838

Text #1

Max Range: 2.6564. Min Range: -2.6564

Max Act: 2.5081. Min Act: 0.0000

Data Index: 426604 (C4 (Web Text))

Max Activating Token Index: 170

Text #2

Max Range: 2.6564. Min Range: -2.6564

Max Act: 2.2044. Min Act: -0.0000

Data Index: 279529 (C4 (Web Text))

Max Activating Token Index: 580

Text #3

Max Range: 2.6564. Min Range: -2.6564

Max Act: 1.9475. Min Act: -0.0000

Data Index: 912842 (C4 (Web Text))

Max Activating Token Index: 343

Text #4

Max Range: 2.6564. Min Range: -2.6564

Max Act: 1.9094. Min Act: -0.0000

Data Index: 35970 (C4 (Web Text))

Max Activating Token Index: 667

Text #5

Max Range: 2.6564. Min Range: -2.6564

Max Act: 1.7416. Min Act: -0.0000

Data Index: 1044781 (C4 (Web Text))

Max Activating Token Index: 91

Text #6

Max Range: 2.6564. Min Range: -2.6564

Max Act: 1.6051. Min Act: -0.0000

Data Index: 920024 (C4 (Web Text))

Max Activating Token Index: 164

Text #7

Max Range: 2.6564. Min Range: -2.6564

Max Act: 1.6052. Min Act: 0.0000

Data Index: 342718 (C4 (Web Text))

Max Activating Token Index: 80

Text #8

Max Range: 2.6564. Min Range: -2.6564

Max Act: 1.5610. Min Act: -0.0000

Data Index: 375594 (C4 (Web Text))

Max Activating Token Index: 787

Text #9

Max Range: 2.6564. Min Range: -2.6564

Max Act: 1.5537. Min Act: -0.0000

Data Index: 135666 (C4 (Web Text))

Max Activating Token Index: 465

Text #10

Max Range: 2.6564. Min Range: -2.6564

Max Act: 1.4973. Min Act: -0.0000

Data Index: 353196 (C4 (Web Text))

Max Activating Token Index: 327

Text #11

Max Range: 2.6564. Min Range: -2.6564

Max Act: 1.5303. Min Act: -0.0000

Data Index: 710617 (C4 (Web Text))

Max Activating Token Index: 486

Text #12

Max Range: 2.6564. Min Range: -2.6564

Max Act: 1.4538. Min Act: -0.0000

Data Index: 1209537 (C4 (Web Text))

Max Activating Token Index: 910

Text #13

Max Range: 2.6564. Min Range: -2.6564

Max Act: 1.4327. Min Act: -0.0000

Data Index: 1069412 (C4 (Web Text))

Max Activating Token Index: 939

Text #14

Max Range: 2.6564. Min Range: -2.6564

Max Act: 1.4177. Min Act: -0.0000

Data Index: 540070 (C4 (Web Text))

Max Activating Token Index: 159

Text #15

Max Range: 2.6564. Min Range: -2.6564

Max Act: 1.4025. Min Act: -0.0000

Data Index: 219231 (C4 (Web Text))

Max Activating Token Index: 575

Text #16

Max Range: 2.6564. Min Range: -2.6564

Max Act: 1.3892. Min Act: -0.0000

Data Index: 362252 (C4 (Web Text))

Max Activating Token Index: 988

Text #17

Max Range: 2.6564. Min Range: -2.6564

Max Act: 1.4189. Min Act: -0.0000

Data Index: 161682 (C4 (Web Text))

Max Activating Token Index: 211

Text #18

Max Range: 2.6564. Min Range: -2.6564

Max Act: 1.3345. Min Act: -0.0000

Data Index: 292023 (C4 (Web Text))

Max Activating Token Index: 186

Text #19

Max Range: 2.6564. Min Range: -2.6564

Max Act: 1.4380. Min Act: -0.0000

Data Index: 1358758 (C4 (Web Text))

Max Activating Token Index: 728