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

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

Neuron 3166 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: 1.2214. Min Range: -1.2214

Max Act: 1.2214. Min Act: -0.0002

Data Index: 195057 (C4 (Web Text))

Max Activating Token Index: 745

Text #1

Max Range: 1.2214. Min Range: -1.2214

Max Act: 1.1700. Min Act: -0.0002

Data Index: 316596 (C4 (Web Text))

Max Activating Token Index: 111

Text #2

Max Range: 1.2214. Min Range: -1.2214

Max Act: 1.1229. Min Act: -0.0002

Data Index: 998314 (C4 (Web Text))

Max Activating Token Index: 659

Text #3

Max Range: 1.2214. Min Range: -1.2214

Max Act: 1.2148. Min Act: -0.0002

Data Index: 1119418 (C4 (Web Text))

Max Activating Token Index: 684

Text #4

Max Range: 1.2214. Min Range: -1.2214

Max Act: 1.1982. Min Act: -0.0002

Data Index: 1074635 (C4 (Web Text))

Max Activating Token Index: 495

Text #5

Max Range: 1.2214. Min Range: -1.2214

Max Act: 1.1268. Min Act: -0.0002

Data Index: 1104337 (C4 (Web Text))

Max Activating Token Index: 13

Text #6

Max Range: 1.2214. Min Range: -1.2214

Max Act: 0.9620. Min Act: -0.0002

Data Index: 538876 (C4 (Web Text))

Max Activating Token Index: 520

Text #7

Max Range: 1.2214. Min Range: -1.2214

Max Act: 1.1942. Min Act: -0.0002

Data Index: 820090 (C4 (Web Text))

Max Activating Token Index: 950

Text #8

Max Range: 1.2214. Min Range: -1.2214

Max Act: 0.9827. Min Act: -0.0002

Data Index: 801365 (C4 (Web Text))

Max Activating Token Index: 93

Text #9

Max Range: 1.2214. Min Range: -1.2214

Max Act: 1.0478. Min Act: -0.0002

Data Index: 4005 (C4 (Web Text))

Max Activating Token Index: 357

Text #10

Max Range: 1.2214. Min Range: -1.2214

Max Act: 0.9939. Min Act: -0.0002

Data Index: 1104702 (C4 (Web Text))

Max Activating Token Index: 966

Text #11

Max Range: 1.2214. Min Range: -1.2214

Max Act: 1.0435. Min Act: -0.0002

Data Index: 389262 (C4 (Web Text))

Max Activating Token Index: 58

Text #12

Max Range: 1.2214. Min Range: -1.2214

Max Act: 0.9826. Min Act: -0.0002

Data Index: 858057 (C4 (Web Text))

Max Activating Token Index: 338

Text #13

Max Range: 1.2214. Min Range: -1.2214

Max Act: 1.0530. Min Act: -0.0002

Data Index: 646942 (C4 (Web Text))

Max Activating Token Index: 371

Text #14

Max Range: 1.2214. Min Range: -1.2214

Max Act: 1.0362. Min Act: -0.0002

Data Index: 827893 (C4 (Web Text))

Max Activating Token Index: 906

Text #15

Max Range: 1.2214. Min Range: -1.2214

Max Act: 0.9964. Min Act: -0.0002

Data Index: 82877 (C4 (Web Text))

Max Activating Token Index: 440

Text #16

Max Range: 1.2214. Min Range: -1.2214

Max Act: 1.0842. Min Act: -0.0002

Data Index: 470078 (C4 (Web Text))

Max Activating Token Index: 53

Text #17

Max Range: 1.2214. Min Range: -1.2214

Max Act: 1.0862. Min Act: -0.0002

Data Index: 1007416 (C4 (Web Text))

Max Activating Token Index: 746

Text #18

Max Range: 1.2214. Min Range: -1.2214

Max Act: 1.0562. Min Act: -0.0002

Data Index: 800002 (C4 (Web Text))

Max Activating Token Index: 630

Text #19

Max Range: 1.2214. Min Range: -1.2214

Max Act: 1.1071. Min Act: -0.0002

Data Index: 1324654 (C4 (Web Text))

Max Activating Token Index: 137