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

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

Neuron 3064 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7125. Min Range: -0.7125

Max Act: 0.7125. Min Act: -0.0000

Data Index: 1150666 (C4 (Web Text))

Max Activating Token Index: 954

Text #1

Max Range: 0.7125. Min Range: -0.7125

Max Act: 0.6500. Min Act: -0.0000

Data Index: 166660 (C4 (Web Text))

Max Activating Token Index: 900

Text #2

Max Range: 0.7125. Min Range: -0.7125

Max Act: 0.6606. Min Act: -0.0000

Data Index: 133063 (C4 (Web Text))

Max Activating Token Index: 940

Text #3

Max Range: 0.7125. Min Range: -0.7125

Max Act: 0.6513. Min Act: -0.0000

Data Index: 512258 (C4 (Web Text))

Max Activating Token Index: 448

Text #4

Max Range: 0.7125. Min Range: -0.7125

Max Act: 0.6249. Min Act: -0.0000

Data Index: 666400 (C4 (Web Text))

Max Activating Token Index: 197

Text #5

Max Range: 0.7125. Min Range: -0.7125

Max Act: 0.5854. Min Act: -0.0000

Data Index: 1321267 (C4 (Web Text))

Max Activating Token Index: 176

Text #6

Max Range: 0.7125. Min Range: -0.7125

Max Act: 0.6157. Min Act: -0.0000

Data Index: 1306775 (C4 (Web Text))

Max Activating Token Index: 719

Text #7

Max Range: 0.7125. Min Range: -0.7125

Max Act: 0.6179. Min Act: -0.0000

Data Index: 661052 (C4 (Web Text))

Max Activating Token Index: 962

Text #8

Max Range: 0.7125. Min Range: -0.7125

Max Act: 0.6228. Min Act: -0.0000

Data Index: 944834 (C4 (Web Text))

Max Activating Token Index: 122

Text #9

Max Range: 0.7125. Min Range: -0.7125

Max Act: 0.6227. Min Act: -0.0000

Data Index: 1147239 (C4 (Web Text))

Max Activating Token Index: 994

Text #10

Max Range: 0.7125. Min Range: -0.7125

Max Act: 0.6187. Min Act: -0.0000

Data Index: 756309 (C4 (Web Text))

Max Activating Token Index: 266

Text #11

Max Range: 0.7125. Min Range: -0.7125

Max Act: 0.5930. Min Act: -0.0000

Data Index: 56818 (C4 (Web Text))

Max Activating Token Index: 899

Text #12

Max Range: 0.7125. Min Range: -0.7125

Max Act: 0.5982. Min Act: -0.0000

Data Index: 1259536 (C4 (Web Text))

Max Activating Token Index: 285

Text #13

Max Range: 0.7125. Min Range: -0.7125

Max Act: 0.6140. Min Act: -0.0000

Data Index: 418013 (C4 (Web Text))

Max Activating Token Index: 989

Text #14

Max Range: 0.7125. Min Range: -0.7125

Max Act: 0.5891. Min Act: -0.0000

Data Index: 314904 (C4 (Web Text))

Max Activating Token Index: 902

Text #15

Max Range: 0.7125. Min Range: -0.7125

Max Act: 0.5707. Min Act: -0.0000

Data Index: 634463 (C4 (Web Text))

Max Activating Token Index: 164

Text #16

Max Range: 0.7125. Min Range: -0.7125

Max Act: 0.5725. Min Act: -0.0000

Data Index: 648609 (C4 (Web Text))

Max Activating Token Index: 1021

Text #17

Max Range: 0.7125. Min Range: -0.7125

Max Act: 0.5303. Min Act: -0.0000

Data Index: 234981 (C4 (Web Text))

Max Activating Token Index: 712

Text #18

Max Range: 0.7125. Min Range: -0.7125

Max Act: 0.5970. Min Act: -0.0000

Data Index: 782706 (C4 (Web Text))

Max Activating Token Index: 712

Text #19

Max Range: 0.7125. Min Range: -0.7125

Max Act: 0.6541. Min Act: -0.0000

Data Index: 345144 (C4 (Web Text))

Max Activating Token Index: 1020