Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 170 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.3518. Min Range: -0.3518

Max Act: 0.3518. Min Act: -0.0002

Data Index: 83310 (C4 (Web Text))

Max Activating Token Index: 250

Text #1

Max Range: 0.3518. Min Range: -0.3518

Max Act: 0.3105. Min Act: -0.0002

Data Index: 634477 (C4 (Web Text))

Max Activating Token Index: 145

Text #2

Max Range: 0.3518. Min Range: -0.3518

Max Act: 0.3244. Min Act: -0.0002

Data Index: 254870 (C4 (Web Text))

Max Activating Token Index: 299

Text #3

Max Range: 0.3518. Min Range: -0.3518

Max Act: 0.3089. Min Act: -0.0002

Data Index: 828973 (C4 (Web Text))

Max Activating Token Index: 762

Text #4

Max Range: 0.3518. Min Range: -0.3518

Max Act: 0.3212. Min Act: -0.0002

Data Index: 1164148 (C4 (Web Text))

Max Activating Token Index: 994

Text #5

Max Range: 0.3518. Min Range: -0.3518

Max Act: 0.3118. Min Act: -0.0002

Data Index: 685604 (C4 (Web Text))

Max Activating Token Index: 407

Text #6

Max Range: 0.3518. Min Range: -0.3518

Max Act: 0.2970. Min Act: -0.0002

Data Index: 788336 (C4 (Web Text))

Max Activating Token Index: 932

Text #7

Max Range: 0.3518. Min Range: -0.3518

Max Act: 0.3210. Min Act: -0.0002

Data Index: 141555 (C4 (Web Text))

Max Activating Token Index: 773

Text #8

Max Range: 0.3518. Min Range: -0.3518

Max Act: 0.3050. Min Act: -0.0002

Data Index: 725677 (C4 (Web Text))

Max Activating Token Index: 281

Text #9

Max Range: 0.3518. Min Range: -0.3518

Max Act: 0.2976. Min Act: -0.0002

Data Index: 81278 (C4 (Web Text))

Max Activating Token Index: 1002

Text #10

Max Range: 0.3518. Min Range: -0.3518

Max Act: 0.3110. Min Act: -0.0002

Data Index: 1198168 (C4 (Web Text))

Max Activating Token Index: 222

Text #11

Max Range: 0.3518. Min Range: -0.3518

Max Act: 0.2970. Min Act: -0.0002

Data Index: 539389 (C4 (Web Text))

Max Activating Token Index: 203

Text #12

Max Range: 0.3518. Min Range: -0.3518

Max Act: 0.3049. Min Act: -0.0002

Data Index: 155522 (C4 (Web Text))

Max Activating Token Index: 591

Text #13

Max Range: 0.3518. Min Range: -0.3518

Max Act: 0.2955. Min Act: -0.0002

Data Index: 1236577 (C4 (Web Text))

Max Activating Token Index: 16

Text #14

Max Range: 0.3518. Min Range: -0.3518

Max Act: 0.3240. Min Act: -0.0002

Data Index: 1040362 (C4 (Web Text))

Max Activating Token Index: 926

Text #15

Max Range: 0.3518. Min Range: -0.3518

Max Act: 0.2916. Min Act: -0.0002

Data Index: 615273 (C4 (Web Text))

Max Activating Token Index: 72

Text #16

Max Range: 0.3518. Min Range: -0.3518

Max Act: 0.2906. Min Act: -0.0002

Data Index: 789607 (C4 (Web Text))

Max Activating Token Index: 132

Text #17

Max Range: 0.3518. Min Range: -0.3518

Max Act: 0.2810. Min Act: -0.0002

Data Index: 476386 (C4 (Web Text))

Max Activating Token Index: 34

Text #18

Max Range: 0.3518. Min Range: -0.3518

Max Act: 0.2870. Min Act: -0.0002

Data Index: 842030 (C4 (Web Text))

Max Activating Token Index: 47

Text #19

Max Range: 0.3518. Min Range: -0.3518

Max Act: 0.2847. Min Act: -0.0002

Data Index: 99446 (C4 (Web Text))

Max Activating Token Index: 903