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

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

Neuron 243 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4201. Min Range: -0.4201

Max Act: 0.4201. Min Act: -0.0000

Data Index: 897575 (C4 (Web Text))

Max Activating Token Index: 703

Text #1

Max Range: 0.4201. Min Range: -0.4201

Max Act: 0.3665. Min Act: -0.0000

Data Index: 529090 (C4 (Web Text))

Max Activating Token Index: 293

Text #2

Max Range: 0.4201. Min Range: -0.4201

Max Act: 0.3583. Min Act: -0.0000

Data Index: 727450 (C4 (Web Text))

Max Activating Token Index: 765

Text #3

Max Range: 0.4201. Min Range: -0.4201

Max Act: 0.3669. Min Act: -0.0000

Data Index: 844385 (C4 (Web Text))

Max Activating Token Index: 868

Text #4

Max Range: 0.4201. Min Range: -0.4201

Max Act: 0.3478. Min Act: -0.0000

Data Index: 596540 (C4 (Web Text))

Max Activating Token Index: 786

Text #5

Max Range: 0.4201. Min Range: -0.4201

Max Act: 0.3296. Min Act: -0.0000

Data Index: 1349379 (C4 (Web Text))

Max Activating Token Index: 943

Text #6

Max Range: 0.4201. Min Range: -0.4201

Max Act: 0.3275. Min Act: -0.0000

Data Index: 231144 (C4 (Web Text))

Max Activating Token Index: 172

Text #7

Max Range: 0.4201. Min Range: -0.4201

Max Act: 0.3247. Min Act: -0.0000

Data Index: 73717 (C4 (Web Text))

Max Activating Token Index: 595

Text #8

Max Range: 0.4201. Min Range: -0.4201

Max Act: 0.3190. Min Act: -0.0000

Data Index: 177759 (C4 (Web Text))

Max Activating Token Index: 983

Text #9

Max Range: 0.4201. Min Range: -0.4201

Max Act: 0.3134. Min Act: -0.0000

Data Index: 1061598 (C4 (Web Text))

Max Activating Token Index: 83

Text #10

Max Range: 0.4201. Min Range: -0.4201

Max Act: 0.3251. Min Act: -0.0000

Data Index: 847976 (C4 (Web Text))

Max Activating Token Index: 209

Text #11

Max Range: 0.4201. Min Range: -0.4201

Max Act: 0.3216. Min Act: -0.0000

Data Index: 680293 (C4 (Web Text))

Max Activating Token Index: 370

Text #12

Max Range: 0.4201. Min Range: -0.4201

Max Act: 0.3194. Min Act: -0.0000

Data Index: 1154152 (C4 (Web Text))

Max Activating Token Index: 110

Text #13

Max Range: 0.4201. Min Range: -0.4201

Max Act: 0.2980. Min Act: -0.0000

Data Index: 1053646 (C4 (Web Text))

Max Activating Token Index: 116

Text #14

Max Range: 0.4201. Min Range: -0.4201

Max Act: 0.3037. Min Act: -0.0000

Data Index: 465472 (C4 (Web Text))

Max Activating Token Index: 965

Text #15

Max Range: 0.4201. Min Range: -0.4201

Max Act: 0.3030. Min Act: 0.0000

Data Index: 716675 (C4 (Web Text))

Max Activating Token Index: 803

Text #16

Max Range: 0.4201. Min Range: -0.4201

Max Act: 0.3033. Min Act: 0.0001

Data Index: 1122408 (C4 (Web Text))

Max Activating Token Index: 876

Text #17

Max Range: 0.4201. Min Range: -0.4201

Max Act: 0.3190. Min Act: -0.0000

Data Index: 373399 (C4 (Web Text))

Max Activating Token Index: 654

Text #18

Max Range: 0.4201. Min Range: -0.4201

Max Act: 0.3049. Min Act: -0.0000

Data Index: 907752 (C4 (Web Text))

Max Activating Token Index: 837

Text #19

Max Range: 0.4201. Min Range: -0.4201

Max Act: 0.3060. Min Act: -0.0000

Data Index: 921774 (C4 (Web Text))

Max Activating Token Index: 687