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

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

Neuron 934 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: 0.5837. Min Range: -0.5837

Max Act: 0.5837. Min Act: -0.0003

Data Index: 1015837 (C4 (Web Text))

Max Activating Token Index: 837

Text #1

Max Range: 0.5837. Min Range: -0.5837

Max Act: 0.5148. Min Act: -0.0003

Data Index: 1075016 (C4 (Web Text))

Max Activating Token Index: 89

Text #2

Max Range: 0.5837. Min Range: -0.5837

Max Act: 0.4725. Min Act: -0.0003

Data Index: 1109914 (C4 (Web Text))

Max Activating Token Index: 100

Text #3

Max Range: 0.5837. Min Range: -0.5837

Max Act: 0.4638. Min Act: -0.0003

Data Index: 864383 (C4 (Web Text))

Max Activating Token Index: 260

Text #4

Max Range: 0.5837. Min Range: -0.5837

Max Act: 0.4363. Min Act: -0.0002

Data Index: 209130 (C4 (Web Text))

Max Activating Token Index: 261

Text #5

Max Range: 0.5837. Min Range: -0.5837

Max Act: 0.4218. Min Act: -0.0002

Data Index: 207036 (C4 (Web Text))

Max Activating Token Index: 557

Text #6

Max Range: 0.5837. Min Range: -0.5837

Max Act: 0.4218. Min Act: -0.0003

Data Index: 909891 (C4 (Web Text))

Max Activating Token Index: 199

Text #7

Max Range: 0.5837. Min Range: -0.5837

Max Act: 0.3914. Min Act: -0.0002

Data Index: 1203921 (C4 (Web Text))

Max Activating Token Index: 600

Text #8

Max Range: 0.5837. Min Range: -0.5837

Max Act: 0.4187. Min Act: -0.0003

Data Index: 1167327 (C4 (Web Text))

Max Activating Token Index: 566

Text #9

Max Range: 0.5837. Min Range: -0.5837

Max Act: 0.4154. Min Act: -0.0003

Data Index: 1008220 (C4 (Web Text))

Max Activating Token Index: 422

Text #10

Max Range: 0.5837. Min Range: -0.5837

Max Act: 0.4129. Min Act: -0.0003

Data Index: 23499 (C4 (Web Text))

Max Activating Token Index: 464

Text #11

Max Range: 0.5837. Min Range: -0.5837

Max Act: 0.3835. Min Act: -0.0002

Data Index: 968199 (C4 (Web Text))

Max Activating Token Index: 262

Text #12

Max Range: 0.5837. Min Range: -0.5837

Max Act: 0.4103. Min Act: -0.0003

Data Index: 108240 (C4 (Web Text))

Max Activating Token Index: 1007

Text #13

Max Range: 0.5837. Min Range: -0.5837

Max Act: 0.4099. Min Act: -0.0003

Data Index: 743374 (C4 (Web Text))

Max Activating Token Index: 106

Text #14

Max Range: 0.5837. Min Range: -0.5837

Max Act: 0.4085. Min Act: -0.0002

Data Index: 1231007 (C4 (Web Text))

Max Activating Token Index: 159

Text #15

Max Range: 0.5837. Min Range: -0.5837

Max Act: 0.3763. Min Act: -0.0003

Data Index: 284768 (C4 (Web Text))

Max Activating Token Index: 381

Text #16

Max Range: 0.5837. Min Range: -0.5837

Max Act: 0.4033. Min Act: -0.0003

Data Index: 1090594 (C4 (Web Text))

Max Activating Token Index: 910

Text #17

Max Range: 0.5837. Min Range: -0.5837

Max Act: 0.4002. Min Act: -0.0003

Data Index: 905082 (C4 (Web Text))

Max Activating Token Index: 164

Text #18

Max Range: 0.5837. Min Range: -0.5837

Max Act: 0.3928. Min Act: -0.0003

Data Index: 601892 (C4 (Web Text))

Max Activating Token Index: 894

Text #19

Max Range: 0.5837. Min Range: -0.5837

Max Act: 0.3918. Min Act: -0.0003

Data Index: 1075107 (C4 (Web Text))

Max Activating Token Index: 544