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

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

Neuron 2340 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: 5.1074. Min Range: -5.1074

Max Act: 5.0380. Min Act: -0.0002

Data Index: 670734 (C4 (Web Text))

Max Activating Token Index: 500

Text #1

Max Range: 5.1074. Min Range: -5.1074

Max Act: 5.1074. Min Act: -0.0002

Data Index: 1224900 (C4 (Web Text))

Max Activating Token Index: 54

Text #2

Max Range: 5.1074. Min Range: -5.1074

Max Act: 4.8208. Min Act: -0.0002

Data Index: 1027078 (C4 (Web Text))

Max Activating Token Index: 491

Text #3

Max Range: 5.1074. Min Range: -5.1074

Max Act: 4.5646. Min Act: -0.0002

Data Index: 733957 (C4 (Web Text))

Max Activating Token Index: 866

Text #4

Max Range: 5.1074. Min Range: -5.1074

Max Act: 4.4037. Min Act: -0.0002

Data Index: 973630 (C4 (Web Text))

Max Activating Token Index: 407

Text #5

Max Range: 5.1074. Min Range: -5.1074

Max Act: 4.8412. Min Act: -0.0002

Data Index: 626135 (C4 (Web Text))

Max Activating Token Index: 736

Text #6

Max Range: 5.1074. Min Range: -5.1074

Max Act: 4.6786. Min Act: -0.0002

Data Index: 176092 (C4 (Web Text))

Max Activating Token Index: 515

Text #7

Max Range: 5.1074. Min Range: -5.1074

Max Act: 4.5008. Min Act: -0.0002

Data Index: 1283535 (C4 (Web Text))

Max Activating Token Index: 295

Text #8

Max Range: 5.1074. Min Range: -5.1074

Max Act: 4.6362. Min Act: -0.0002

Data Index: 583256 (C4 (Web Text))

Max Activating Token Index: 498

Text #9

Max Range: 5.1074. Min Range: -5.1074

Max Act: 4.5559. Min Act: -0.0002

Data Index: 82361 (C4 (Web Text))

Max Activating Token Index: 283

Text #10

Max Range: 5.1074. Min Range: -5.1074

Max Act: 4.5418. Min Act: -0.0002

Data Index: 62130 (C4 (Web Text))

Max Activating Token Index: 134

Text #11

Max Range: 5.1074. Min Range: -5.1074

Max Act: 4.5915. Min Act: -0.0002

Data Index: 163968 (C4 (Web Text))

Max Activating Token Index: 18

Text #12

Max Range: 5.1074. Min Range: -5.1074

Max Act: 4.2713. Min Act: -0.0002

Data Index: 609712 (C4 (Web Text))

Max Activating Token Index: 218

Text #13

Max Range: 5.1074. Min Range: -5.1074

Max Act: 4.2980. Min Act: -0.0002

Data Index: 1094026 (C4 (Web Text))

Max Activating Token Index: 228

Text #14

Max Range: 5.1074. Min Range: -5.1074

Max Act: 4.4150. Min Act: -0.0002

Data Index: 341401 (C4 (Web Text))

Max Activating Token Index: 457

Text #15

Max Range: 5.1074. Min Range: -5.1074

Max Act: 4.3801. Min Act: -0.0002

Data Index: 1004284 (C4 (Web Text))

Max Activating Token Index: 115

Text #16

Max Range: 5.1074. Min Range: -5.1074

Max Act: 4.3745. Min Act: -0.0002

Data Index: 594756 (C4 (Web Text))

Max Activating Token Index: 241

Text #17

Max Range: 5.1074. Min Range: -5.1074

Max Act: 4.0429. Min Act: -0.0002

Data Index: 43481 (C4 (Web Text))

Max Activating Token Index: 315

Text #18

Max Range: 5.1074. Min Range: -5.1074

Max Act: 4.2658. Min Act: -0.0002

Data Index: 60989 (C4 (Web Text))

Max Activating Token Index: 301

Text #19

Max Range: 5.1074. Min Range: -5.1074

Max Act: 4.4201. Min Act: -0.0002

Data Index: 215562 (C4 (Web Text))

Max Activating Token Index: 721