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

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

Neuron 5080 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.0167. Min Range: -4.0167

Max Act: 4.0167. Min Act: -0.0001

Data Index: 969814 (C4 (Web Text))

Max Activating Token Index: 66

Text #1

Max Range: 4.0167. Min Range: -4.0167

Max Act: 3.8686. Min Act: -0.0001

Data Index: 237352 (C4 (Web Text))

Max Activating Token Index: 93

Text #2

Max Range: 4.0167. Min Range: -4.0167

Max Act: 3.7222. Min Act: -0.0001

Data Index: 59879 (C4 (Web Text))

Max Activating Token Index: 115

Text #3

Max Range: 4.0167. Min Range: -4.0167

Max Act: 3.7041. Min Act: -0.0000

Data Index: 882105 (C4 (Web Text))

Max Activating Token Index: 94

Text #4

Max Range: 4.0167. Min Range: -4.0167

Max Act: 3.8600. Min Act: -0.0001

Data Index: 841220 (C4 (Web Text))

Max Activating Token Index: 60

Text #5

Max Range: 4.0167. Min Range: -4.0167

Max Act: 3.2797. Min Act: -0.0000

Data Index: 286050 (C4 (Web Text))

Max Activating Token Index: 28

Text #6

Max Range: 4.0167. Min Range: -4.0167

Max Act: 3.1884. Min Act: -0.0001

Data Index: 1257996 (C4 (Web Text))

Max Activating Token Index: 145

Text #7

Max Range: 4.0167. Min Range: -4.0167

Max Act: 3.1707. Min Act: -0.0000

Data Index: 639663 (C4 (Web Text))

Max Activating Token Index: 156

Text #8

Max Range: 4.0167. Min Range: -4.0167

Max Act: 3.3223. Min Act: -0.0001

Data Index: 1063897 (C4 (Web Text))

Max Activating Token Index: 156

Text #9

Max Range: 4.0167. Min Range: -4.0167

Max Act: 3.0998. Min Act: -0.0001

Data Index: 1197986 (C4 (Web Text))

Max Activating Token Index: 393

Text #10

Max Range: 4.0167. Min Range: -4.0167

Max Act: 2.9125. Min Act: -0.0001

Data Index: 791258 (C4 (Web Text))

Max Activating Token Index: 750

Text #11

Max Range: 4.0167. Min Range: -4.0167

Max Act: 2.8027. Min Act: -0.0000

Data Index: 1358996 (C4 (Web Text))

Max Activating Token Index: 337

Text #12

Max Range: 4.0167. Min Range: -4.0167

Max Act: 3.0657. Min Act: -0.0000

Data Index: 515280 (C4 (Web Text))

Max Activating Token Index: 450

Text #13

Max Range: 4.0167. Min Range: -4.0167

Max Act: 2.7982. Min Act: -0.0000

Data Index: 950084 (C4 (Web Text))

Max Activating Token Index: 493

Text #14

Max Range: 4.0167. Min Range: -4.0167

Max Act: 2.9326. Min Act: -0.0000

Data Index: 1275150 (C4 (Web Text))

Max Activating Token Index: 377

Text #15

Max Range: 4.0167. Min Range: -4.0167

Max Act: 2.7718. Min Act: -0.0001

Data Index: 251798 (C4 (Web Text))

Max Activating Token Index: 477

Text #16

Max Range: 4.0167. Min Range: -4.0167

Max Act: 2.7980. Min Act: -0.0000

Data Index: 40876 (C4 (Web Text))

Max Activating Token Index: 355

Text #17

Max Range: 4.0167. Min Range: -4.0167

Max Act: 2.6497. Min Act: -0.0001

Data Index: 734289 (C4 (Web Text))

Max Activating Token Index: 537

Text #18

Max Range: 4.0167. Min Range: -4.0167

Max Act: 2.4005. Min Act: -0.0001

Data Index: 574866 (C4 (Web Text))

Max Activating Token Index: 660

Text #19

Max Range: 4.0167. Min Range: -4.0167

Max Act: 2.3977. Min Act: -0.0001

Data Index: 657015 (C4 (Web Text))

Max Activating Token Index: 672