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

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

Neuron 2027 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6634. Min Range: -0.6634

Max Act: 0.6634. Min Act: -0.0000

Data Index: 1235127 (C4 (Web Text))

Max Activating Token Index: 630

Text #1

Max Range: 0.6634. Min Range: -0.6634

Max Act: 0.6610. Min Act: -0.0000

Data Index: 620211 (C4 (Web Text))

Max Activating Token Index: 183

Text #2

Max Range: 0.6634. Min Range: -0.6634

Max Act: 0.5900. Min Act: -0.0000

Data Index: 843343 (C4 (Web Text))

Max Activating Token Index: 192

Text #3

Max Range: 0.6634. Min Range: -0.6634

Max Act: 0.4912. Min Act: -0.0000

Data Index: 1280779 (C4 (Web Text))

Max Activating Token Index: 123

Text #4

Max Range: 0.6634. Min Range: -0.6634

Max Act: 0.5575. Min Act: -0.0000

Data Index: 1239905 (C4 (Web Text))

Max Activating Token Index: 357

Text #5

Max Range: 0.6634. Min Range: -0.6634

Max Act: 0.4842. Min Act: -0.0000

Data Index: 444841 (C4 (Web Text))

Max Activating Token Index: 738

Text #6

Max Range: 0.6634. Min Range: -0.6634

Max Act: 0.3555. Min Act: -0.0000

Data Index: 845232 (C4 (Web Text))

Max Activating Token Index: 754

Text #7

Max Range: 0.6634. Min Range: -0.6634

Max Act: 0.2998. Min Act: -0.0000

Data Index: 719012 (C4 (Web Text))

Max Activating Token Index: 274

Text #8

Max Range: 0.6634. Min Range: -0.6634

Max Act: 0.3382. Min Act: -0.0000

Data Index: 1117751 (C4 (Web Text))

Max Activating Token Index: 885

Text #9

Max Range: 0.6634. Min Range: -0.6634

Max Act: 0.3156. Min Act: -0.0000

Data Index: 54223 (C4 (Web Text))

Max Activating Token Index: 364

Text #10

Max Range: 0.6634. Min Range: -0.6634

Max Act: 0.3212. Min Act: -0.0000

Data Index: 704946 (C4 (Web Text))

Max Activating Token Index: 539

Text #11

Max Range: 0.6634. Min Range: -0.6634

Max Act: 0.2985. Min Act: -0.0000

Data Index: 387483 (C4 (Web Text))

Max Activating Token Index: 594

Text #12

Max Range: 0.6634. Min Range: -0.6634

Max Act: 0.3171. Min Act: -0.0000

Data Index: 1159766 (C4 (Web Text))

Max Activating Token Index: 1017

Text #13

Max Range: 0.6634. Min Range: -0.6634

Max Act: 0.3239. Min Act: -0.0000

Data Index: 1109915 (C4 (Web Text))

Max Activating Token Index: 702

Text #14

Max Range: 0.6634. Min Range: -0.6634

Max Act: 0.3124. Min Act: -0.0000

Data Index: 158035 (C4 (Web Text))

Max Activating Token Index: 111

Text #15

Max Range: 0.6634. Min Range: -0.6634

Max Act: 0.3032. Min Act: -0.0000

Data Index: 621065 (C4 (Web Text))

Max Activating Token Index: 247

Text #16

Max Range: 0.6634. Min Range: -0.6634

Max Act: 0.3182. Min Act: -0.0000

Data Index: 1159767 (C4 (Web Text))

Max Activating Token Index: 146

Text #17

Max Range: 0.6634. Min Range: -0.6634

Max Act: 0.3066. Min Act: -0.0000

Data Index: 31587 (C4 (Web Text))

Max Activating Token Index: 984

Text #18

Max Range: 0.6634. Min Range: -0.6634

Max Act: 0.3074. Min Act: -0.0000

Data Index: 50109 (C4 (Web Text))

Max Activating Token Index: 924

Text #19

Max Range: 0.6634. Min Range: -0.6634

Max Act: 0.3232. Min Act: -0.0000

Data Index: 1262200 (C4 (Web Text))

Max Activating Token Index: 399