Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4998 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.2048. Min Range: -1.2048

Max Act: 1.2048. Min Act: -0.0002

Data Index: 1064431 (C4 (Web Text))

Max Activating Token Index: 130

Text #1

Max Range: 1.2048. Min Range: -1.2048

Max Act: 1.1652. Min Act: -0.0002

Data Index: 1346337 (C4 (Web Text))

Max Activating Token Index: 52

Text #2

Max Range: 1.2048. Min Range: -1.2048

Max Act: 1.0532. Min Act: -0.0002

Data Index: 931150 (C4 (Web Text))

Max Activating Token Index: 128

Text #3

Max Range: 1.2048. Min Range: -1.2048

Max Act: 0.8679. Min Act: -0.0002

Data Index: 68894 (C4 (Web Text))

Max Activating Token Index: 27

Text #4

Max Range: 1.2048. Min Range: -1.2048

Max Act: 0.8771. Min Act: -0.0002

Data Index: 1164390 (C4 (Web Text))

Max Activating Token Index: 153

Text #5

Max Range: 1.2048. Min Range: -1.2048

Max Act: 0.8362. Min Act: -0.0002

Data Index: 910771 (C4 (Web Text))

Max Activating Token Index: 707

Text #6

Max Range: 1.2048. Min Range: -1.2048

Max Act: 0.8110. Min Act: -0.0002

Data Index: 1139455 (C4 (Web Text))

Max Activating Token Index: 692

Text #7

Max Range: 1.2048. Min Range: -1.2048

Max Act: 0.7718. Min Act: -0.0002

Data Index: 913530 (C4 (Web Text))

Max Activating Token Index: 687

Text #8

Max Range: 1.2048. Min Range: -1.2048

Max Act: 0.7639. Min Act: -0.0002

Data Index: 1194739 (C4 (Web Text))

Max Activating Token Index: 239

Text #9

Max Range: 1.2048. Min Range: -1.2048

Max Act: 0.7121. Min Act: -0.0002

Data Index: 185378 (C4 (Web Text))

Max Activating Token Index: 12

Text #10

Max Range: 1.2048. Min Range: -1.2048

Max Act: 0.7095. Min Act: -0.0002

Data Index: 1237247 (C4 (Web Text))

Max Activating Token Index: 7

Text #11

Max Range: 1.2048. Min Range: -1.2048

Max Act: 0.7199. Min Act: -0.0002

Data Index: 117845 (C4 (Web Text))

Max Activating Token Index: 216

Text #12

Max Range: 1.2048. Min Range: -1.2048

Max Act: 0.6938. Min Act: -0.0002

Data Index: 886693 (C4 (Web Text))

Max Activating Token Index: 189

Text #13

Max Range: 1.2048. Min Range: -1.2048

Max Act: 0.6534. Min Act: -0.0002

Data Index: 931700 (C4 (Web Text))

Max Activating Token Index: 164

Text #14

Max Range: 1.2048. Min Range: -1.2048

Max Act: 0.6680. Min Act: -0.0002

Data Index: 481281 (C4 (Web Text))

Max Activating Token Index: 427

Text #15

Max Range: 1.2048. Min Range: -1.2048

Max Act: 0.6667. Min Act: -0.0002

Data Index: 1088427 (C4 (Web Text))

Max Activating Token Index: 324

Text #16

Max Range: 1.2048. Min Range: -1.2048

Max Act: 0.6386. Min Act: -0.0002

Data Index: 322518 (C4 (Web Text))

Max Activating Token Index: 511

Text #17

Max Range: 1.2048. Min Range: -1.2048

Max Act: 0.6602. Min Act: -0.0002

Data Index: 308541 (C4 (Web Text))

Max Activating Token Index: 151

Text #18

Max Range: 1.2048. Min Range: -1.2048

Max Act: 0.6499. Min Act: -0.0002

Data Index: 873200 (C4 (Web Text))

Max Activating Token Index: 364

Text #19

Max Range: 1.2048. Min Range: -1.2048

Max Act: 0.6395. Min Act: -0.0002

Data Index: 1202038 (C4 (Web Text))

Max Activating Token Index: 870