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

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

Neuron 4184 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4874. Min Range: -0.4874

Max Act: 0.4874. Min Act: -0.0003

Data Index: 488768 (C4 (Web Text))

Max Activating Token Index: 278

Text #1

Max Range: 0.4874. Min Range: -0.4874

Max Act: 0.4788. Min Act: -0.0003

Data Index: 205006 (C4 (Web Text))

Max Activating Token Index: 216

Text #2

Max Range: 0.4874. Min Range: -0.4874

Max Act: 0.4301. Min Act: -0.0003

Data Index: 281021 (C4 (Web Text))

Max Activating Token Index: 312

Text #3

Max Range: 0.4874. Min Range: -0.4874

Max Act: 0.4148. Min Act: -0.0003

Data Index: 643764 (C4 (Web Text))

Max Activating Token Index: 654

Text #4

Max Range: 0.4874. Min Range: -0.4874

Max Act: 0.4171. Min Act: -0.0003

Data Index: 25688 (C4 (Web Text))

Max Activating Token Index: 173

Text #5

Max Range: 0.4874. Min Range: -0.4874

Max Act: 0.4105. Min Act: -0.0003

Data Index: 778301 (C4 (Web Text))

Max Activating Token Index: 337

Text #6

Max Range: 0.4874. Min Range: -0.4874

Max Act: 0.4088. Min Act: -0.0003

Data Index: 879666 (C4 (Web Text))

Max Activating Token Index: 154

Text #7

Max Range: 0.4874. Min Range: -0.4874

Max Act: 0.4169. Min Act: -0.0003

Data Index: 1228923 (C4 (Web Text))

Max Activating Token Index: 100

Text #8

Max Range: 0.4874. Min Range: -0.4874

Max Act: 0.3858. Min Act: -0.0003

Data Index: 88016 (C4 (Web Text))

Max Activating Token Index: 286

Text #9

Max Range: 0.4874. Min Range: -0.4874

Max Act: 0.3829. Min Act: -0.0003

Data Index: 85622 (C4 (Web Text))

Max Activating Token Index: 524

Text #10

Max Range: 0.4874. Min Range: -0.4874

Max Act: 0.3910. Min Act: -0.0003

Data Index: 503706 (C4 (Web Text))

Max Activating Token Index: 522

Text #11

Max Range: 0.4874. Min Range: -0.4874

Max Act: 0.4034. Min Act: -0.0003

Data Index: 602790 (C4 (Web Text))

Max Activating Token Index: 797

Text #12

Max Range: 0.4874. Min Range: -0.4874

Max Act: 0.3854. Min Act: -0.0003

Data Index: 588496 (C4 (Web Text))

Max Activating Token Index: 218

Text #13

Max Range: 0.4874. Min Range: -0.4874

Max Act: 0.3765. Min Act: -0.0003

Data Index: 900856 (C4 (Web Text))

Max Activating Token Index: 203

Text #14

Max Range: 0.4874. Min Range: -0.4874

Max Act: 0.3797. Min Act: -0.0003

Data Index: 833019 (C4 (Web Text))

Max Activating Token Index: 769

Text #15

Max Range: 0.4874. Min Range: -0.4874

Max Act: 0.3753. Min Act: -0.0003

Data Index: 334850 (C4 (Web Text))

Max Activating Token Index: 26

Text #16

Max Range: 0.4874. Min Range: -0.4874

Max Act: 0.3768. Min Act: -0.0003

Data Index: 635139 (C4 (Web Text))

Max Activating Token Index: 213

Text #17

Max Range: 0.4874. Min Range: -0.4874

Max Act: 0.3831. Min Act: -0.0003

Data Index: 1144383 (C4 (Web Text))

Max Activating Token Index: 195

Text #18

Max Range: 0.4874. Min Range: -0.4874

Max Act: 0.3714. Min Act: -0.0003

Data Index: 148387 (C4 (Web Text))

Max Activating Token Index: 197

Text #19

Max Range: 0.4874. Min Range: -0.4874

Max Act: 0.3834. Min Act: -0.0003

Data Index: 316497 (C4 (Web Text))

Max Activating Token Index: 229