Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 842 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.4869. Min Range: -0.4869

Max Act: 0.4869. Min Act: -0.0003

Data Index: 1034211 (C4 (Web Text))

Max Activating Token Index: 139

Text #1

Max Range: 0.4869. Min Range: -0.4869

Max Act: 0.4103. Min Act: -0.0003

Data Index: 909487 (C4 (Web Text))

Max Activating Token Index: 768

Text #2

Max Range: 0.4869. Min Range: -0.4869

Max Act: 0.3751. Min Act: -0.0003

Data Index: 1009167 (C4 (Web Text))

Max Activating Token Index: 195

Text #3

Max Range: 0.4869. Min Range: -0.4869

Max Act: 0.3676. Min Act: -0.0003

Data Index: 642423 (C4 (Web Text))

Max Activating Token Index: 228

Text #4

Max Range: 0.4869. Min Range: -0.4869

Max Act: 0.3647. Min Act: -0.0003

Data Index: 999787 (C4 (Web Text))

Max Activating Token Index: 219

Text #5

Max Range: 0.4869. Min Range: -0.4869

Max Act: 0.3493. Min Act: -0.0003

Data Index: 53973 (C4 (Web Text))

Max Activating Token Index: 250

Text #6

Max Range: 0.4869. Min Range: -0.4869

Max Act: 0.3281. Min Act: -0.0003

Data Index: 299091 (C4 (Web Text))

Max Activating Token Index: 180

Text #7

Max Range: 0.4869. Min Range: -0.4869

Max Act: 0.3207. Min Act: -0.0003

Data Index: 617180 (C4 (Web Text))

Max Activating Token Index: 128

Text #8

Max Range: 0.4869. Min Range: -0.4869

Max Act: 0.3183. Min Act: -0.0003

Data Index: 668059 (C4 (Web Text))

Max Activating Token Index: 341

Text #9

Max Range: 0.4869. Min Range: -0.4869

Max Act: 0.3163. Min Act: -0.0003

Data Index: 1150577 (C4 (Web Text))

Max Activating Token Index: 468

Text #10

Max Range: 0.4869. Min Range: -0.4869

Max Act: 0.3155. Min Act: -0.0003

Data Index: 280848 (C4 (Web Text))

Max Activating Token Index: 821

Text #11

Max Range: 0.4869. Min Range: -0.4869

Max Act: 0.3089. Min Act: -0.0003

Data Index: 802593 (C4 (Web Text))

Max Activating Token Index: 480

Text #12

Max Range: 0.4869. Min Range: -0.4869

Max Act: 0.3001. Min Act: -0.0003

Data Index: 1248200 (C4 (Web Text))

Max Activating Token Index: 477

Text #13

Max Range: 0.4869. Min Range: -0.4869

Max Act: 0.2998. Min Act: -0.0003

Data Index: 490931 (C4 (Web Text))

Max Activating Token Index: 170

Text #14

Max Range: 0.4869. Min Range: -0.4869

Max Act: 0.2991. Min Act: -0.0003

Data Index: 1196656 (C4 (Web Text))

Max Activating Token Index: 103

Text #15

Max Range: 0.4869. Min Range: -0.4869

Max Act: 0.2985. Min Act: -0.0003

Data Index: 1221252 (C4 (Web Text))

Max Activating Token Index: 138

Text #16

Max Range: 0.4869. Min Range: -0.4869

Max Act: 0.2974. Min Act: -0.0003

Data Index: 822446 (C4 (Web Text))

Max Activating Token Index: 572

Text #17

Max Range: 0.4869. Min Range: -0.4869

Max Act: 0.2929. Min Act: -0.0003

Data Index: 207747 (C4 (Web Text))

Max Activating Token Index: 340

Text #18

Max Range: 0.4869. Min Range: -0.4869

Max Act: 0.2911. Min Act: -0.0003

Data Index: 1140376 (C4 (Web Text))

Max Activating Token Index: 259

Text #19

Max Range: 0.4869. Min Range: -0.4869

Max Act: 0.2908. Min Act: -0.0002

Data Index: 224069 (C4 (Web Text))

Max Activating Token Index: 519