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

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

Neuron 2535 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: 0.5118. Min Range: -0.5118

Max Act: 0.5118. Min Act: -0.0000

Data Index: 1288277 (C4 (Web Text))

Max Activating Token Index: 65

Text #1

Max Range: 0.5118. Min Range: -0.5118

Max Act: 0.5022. Min Act: -0.0000

Data Index: 685430 (C4 (Web Text))

Max Activating Token Index: 234

Text #2

Max Range: 0.5118. Min Range: -0.5118

Max Act: 0.4669. Min Act: -0.0000

Data Index: 1120908 (C4 (Web Text))

Max Activating Token Index: 160

Text #3

Max Range: 0.5118. Min Range: -0.5118

Max Act: 0.4459. Min Act: -0.0000

Data Index: 858414 (C4 (Web Text))

Max Activating Token Index: 520

Text #4

Max Range: 0.5118. Min Range: -0.5118

Max Act: 0.4355. Min Act: -0.0000

Data Index: 166327 (C4 (Web Text))

Max Activating Token Index: 341

Text #5

Max Range: 0.5118. Min Range: -0.5118

Max Act: 0.4269. Min Act: -0.0000

Data Index: 380630 (C4 (Web Text))

Max Activating Token Index: 761

Text #6

Max Range: 0.5118. Min Range: -0.5118

Max Act: 0.4013. Min Act: -0.0000

Data Index: 902324 (C4 (Web Text))

Max Activating Token Index: 300

Text #7

Max Range: 0.5118. Min Range: -0.5118

Max Act: 0.4132. Min Act: -0.0000

Data Index: 527433 (C4 (Web Text))

Max Activating Token Index: 763

Text #8

Max Range: 0.5118. Min Range: -0.5118

Max Act: 0.3941. Min Act: -0.0000

Data Index: 167786 (C4 (Web Text))

Max Activating Token Index: 747

Text #9

Max Range: 0.5118. Min Range: -0.5118

Max Act: 0.3892. Min Act: -0.0000

Data Index: 440359 (C4 (Web Text))

Max Activating Token Index: 556

Text #10

Max Range: 0.5118. Min Range: -0.5118

Max Act: 0.3829. Min Act: -0.0000

Data Index: 721712 (C4 (Web Text))

Max Activating Token Index: 371

Text #11

Max Range: 0.5118. Min Range: -0.5118

Max Act: 0.3906. Min Act: -0.0000

Data Index: 604807 (C4 (Web Text))

Max Activating Token Index: 132

Text #12

Max Range: 0.5118. Min Range: -0.5118

Max Act: 0.3745. Min Act: -0.0000

Data Index: 245829 (C4 (Web Text))

Max Activating Token Index: 991

Text #13

Max Range: 0.5118. Min Range: -0.5118

Max Act: 0.3737. Min Act: 0.0000

Data Index: 550554 (C4 (Web Text))

Max Activating Token Index: 384

Text #14

Max Range: 0.5118. Min Range: -0.5118

Max Act: 0.3706. Min Act: -0.0000

Data Index: 1208815 (C4 (Web Text))

Max Activating Token Index: 583

Text #15

Max Range: 0.5118. Min Range: -0.5118

Max Act: 0.3690. Min Act: -0.0000

Data Index: 737243 (C4 (Web Text))

Max Activating Token Index: 117

Text #16

Max Range: 0.5118. Min Range: -0.5118

Max Act: 0.3525. Min Act: -0.0000

Data Index: 1223104 (C4 (Web Text))

Max Activating Token Index: 87

Text #17

Max Range: 0.5118. Min Range: -0.5118

Max Act: 0.3565. Min Act: -0.0000

Data Index: 2030 (C4 (Web Text))

Max Activating Token Index: 47

Text #18

Max Range: 0.5118. Min Range: -0.5118

Max Act: 0.3376. Min Act: -0.0000

Data Index: 248244 (C4 (Web Text))

Max Activating Token Index: 322

Text #19

Max Range: 0.5118. Min Range: -0.5118

Max Act: 0.3652. Min Act: -0.0000

Data Index: 1187243 (C4 (Web Text))

Max Activating Token Index: 888