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

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

Neuron 1054 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4251. Min Range: -1.4251

Max Act: 1.4251. Min Act: -0.0002

Data Index: 1003321 (C4 (Web Text))

Max Activating Token Index: 241

Text #1

Max Range: 1.4251. Min Range: -1.4251

Max Act: 1.2919. Min Act: -0.0002

Data Index: 1060365 (C4 (Web Text))

Max Activating Token Index: 281

Text #2

Max Range: 1.4251. Min Range: -1.4251

Max Act: 1.2907. Min Act: -0.0002

Data Index: 276649 (C4 (Web Text))

Max Activating Token Index: 313

Text #3

Max Range: 1.4251. Min Range: -1.4251

Max Act: 1.1048. Min Act: -0.0002

Data Index: 517856 (C4 (Web Text))

Max Activating Token Index: 941

Text #4

Max Range: 1.4251. Min Range: -1.4251

Max Act: 1.0430. Min Act: -0.0002

Data Index: 856664 (C4 (Web Text))

Max Activating Token Index: 350

Text #5

Max Range: 1.4251. Min Range: -1.4251

Max Act: 1.0994. Min Act: -0.0002

Data Index: 831146 (C4 (Web Text))

Max Activating Token Index: 240

Text #6

Max Range: 1.4251. Min Range: -1.4251

Max Act: 0.9431. Min Act: -0.0002

Data Index: 469103 (C4 (Web Text))

Max Activating Token Index: 63

Text #7

Max Range: 1.4251. Min Range: -1.4251

Max Act: 0.9612. Min Act: -0.0002

Data Index: 753567 (C4 (Web Text))

Max Activating Token Index: 387

Text #8

Max Range: 1.4251. Min Range: -1.4251

Max Act: 0.9302. Min Act: -0.0002

Data Index: 959045 (C4 (Web Text))

Max Activating Token Index: 324

Text #9

Max Range: 1.4251. Min Range: -1.4251

Max Act: 0.8699. Min Act: -0.0002

Data Index: 345182 (C4 (Web Text))

Max Activating Token Index: 735

Text #10

Max Range: 1.4251. Min Range: -1.4251

Max Act: 0.9892. Min Act: -0.0002

Data Index: 324905 (C4 (Web Text))

Max Activating Token Index: 958

Text #11

Max Range: 1.4251. Min Range: -1.4251

Max Act: 0.9889. Min Act: -0.0002

Data Index: 1067596 (C4 (Web Text))

Max Activating Token Index: 276

Text #12

Max Range: 1.4251. Min Range: -1.4251

Max Act: 0.9324. Min Act: -0.0002

Data Index: 979661 (C4 (Web Text))

Max Activating Token Index: 585

Text #13

Max Range: 1.4251. Min Range: -1.4251

Max Act: 0.9290. Min Act: -0.0002

Data Index: 1094795 (C4 (Web Text))

Max Activating Token Index: 68

Text #14

Max Range: 1.4251. Min Range: -1.4251

Max Act: 0.9678. Min Act: -0.0002

Data Index: 186736 (C4 (Web Text))

Max Activating Token Index: 360

Text #15

Max Range: 1.4251. Min Range: -1.4251

Max Act: 0.9213. Min Act: -0.0002

Data Index: 492518 (C4 (Web Text))

Max Activating Token Index: 162

Text #16

Max Range: 1.4251. Min Range: -1.4251

Max Act: 0.8842. Min Act: -0.0002

Data Index: 466893 (C4 (Web Text))

Max Activating Token Index: 186

Text #17

Max Range: 1.4251. Min Range: -1.4251

Max Act: 0.8513. Min Act: -0.0002

Data Index: 773521 (C4 (Web Text))

Max Activating Token Index: 60

Text #18

Max Range: 1.4251. Min Range: -1.4251

Max Act: 0.9046. Min Act: -0.0002

Data Index: 185901 (C4 (Web Text))

Max Activating Token Index: 853

Text #19

Max Range: 1.4251. Min Range: -1.4251

Max Act: 0.8692. Min Act: -0.0002

Data Index: 1187920 (C4 (Web Text))

Max Activating Token Index: 542