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

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

Neuron 4406 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: 0.6027. Min Range: -0.6027

Max Act: 0.5107. Min Act: -0.0000

Data Index: 210601 (C4 (Web Text))

Max Activating Token Index: 221

Text #1

Max Range: 0.6027. Min Range: -0.6027

Max Act: 0.6027. Min Act: -0.0000

Data Index: 8740 (C4 (Web Text))

Max Activating Token Index: 1016

Text #2

Max Range: 0.6027. Min Range: -0.6027

Max Act: 0.5198. Min Act: -0.0000

Data Index: 517741 (C4 (Web Text))

Max Activating Token Index: 106

Text #3

Max Range: 0.6027. Min Range: -0.6027

Max Act: 0.4825. Min Act: -0.0000

Data Index: 41617 (C4 (Web Text))

Max Activating Token Index: 6

Text #4

Max Range: 0.6027. Min Range: -0.6027

Max Act: 0.3976. Min Act: -0.0000

Data Index: 1162937 (C4 (Web Text))

Max Activating Token Index: 518

Text #5

Max Range: 0.6027. Min Range: -0.6027

Max Act: 0.4214. Min Act: -0.0000

Data Index: 535394 (C4 (Web Text))

Max Activating Token Index: 41

Text #6

Max Range: 0.6027. Min Range: -0.6027

Max Act: 0.4299. Min Act: -0.0000

Data Index: 804371 (C4 (Web Text))

Max Activating Token Index: 597

Text #7

Max Range: 0.6027. Min Range: -0.6027

Max Act: 0.3909. Min Act: -0.0000

Data Index: 583944 (C4 (Web Text))

Max Activating Token Index: 398

Text #8

Max Range: 0.6027. Min Range: -0.6027

Max Act: 0.3868. Min Act: -0.0000

Data Index: 706182 (C4 (Web Text))

Max Activating Token Index: 910

Text #9

Max Range: 0.6027. Min Range: -0.6027

Max Act: 0.3961. Min Act: -0.0000

Data Index: 296733 (C4 (Web Text))

Max Activating Token Index: 508

Text #10

Max Range: 0.6027. Min Range: -0.6027

Max Act: 0.4105. Min Act: -0.0000

Data Index: 313032 (C4 (Web Text))

Max Activating Token Index: 620

Text #11

Max Range: 0.6027. Min Range: -0.6027

Max Act: 0.3955. Min Act: -0.0001

Data Index: 366047 (C4 (Web Text))

Max Activating Token Index: 523

Text #12

Max Range: 0.6027. Min Range: -0.6027

Max Act: 0.3681. Min Act: -0.0001

Data Index: 808728 (C4 (Web Text))

Max Activating Token Index: 18

Text #13

Max Range: 0.6027. Min Range: -0.6027

Max Act: 0.3949. Min Act: -0.0000

Data Index: 1314021 (C4 (Web Text))

Max Activating Token Index: 251

Text #14

Max Range: 0.6027. Min Range: -0.6027

Max Act: 0.4482. Min Act: -0.0000

Data Index: 910707 (C4 (Web Text))

Max Activating Token Index: 345

Text #15

Max Range: 0.6027. Min Range: -0.6027

Max Act: 0.4122. Min Act: -0.0001

Data Index: 534253 (C4 (Web Text))

Max Activating Token Index: 677

Text #16

Max Range: 0.6027. Min Range: -0.6027

Max Act: 0.4227. Min Act: -0.0001

Data Index: 198944 (C4 (Web Text))

Max Activating Token Index: 328

Text #17

Max Range: 0.6027. Min Range: -0.6027

Max Act: 0.3761. Min Act: -0.0000

Data Index: 521373 (C4 (Web Text))

Max Activating Token Index: 284

Text #18

Max Range: 0.6027. Min Range: -0.6027

Max Act: 0.4528. Min Act: -0.0001

Data Index: 1247998 (C4 (Web Text))

Max Activating Token Index: 837

Text #19

Max Range: 0.6027. Min Range: -0.6027

Max Act: 0.3771. Min Act: -0.0000

Data Index: 121438 (C4 (Web Text))

Max Activating Token Index: 267