Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3025 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.6371. Min Range: -0.6371

Max Act: 0.6371. Min Act: -0.0000

Data Index: 58224 (C4 (Web Text))

Max Activating Token Index: 58

Text #1

Max Range: 0.6371. Min Range: -0.6371

Max Act: 0.6146. Min Act: -0.0000

Data Index: 44269 (C4 (Web Text))

Max Activating Token Index: 139

Text #2

Max Range: 0.6371. Min Range: -0.6371

Max Act: 0.5825. Min Act: -0.0001

Data Index: 933605 (C4 (Web Text))

Max Activating Token Index: 971

Text #3

Max Range: 0.6371. Min Range: -0.6371

Max Act: 0.5499. Min Act: -0.0000

Data Index: 1008201 (C4 (Web Text))

Max Activating Token Index: 687

Text #4

Max Range: 0.6371. Min Range: -0.6371

Max Act: 0.5225. Min Act: -0.0000

Data Index: 276802 (C4 (Web Text))

Max Activating Token Index: 59

Text #5

Max Range: 0.6371. Min Range: -0.6371

Max Act: 0.5201. Min Act: -0.0001

Data Index: 725602 (C4 (Web Text))

Max Activating Token Index: 761

Text #6

Max Range: 0.6371. Min Range: -0.6371

Max Act: 0.5070. Min Act: -0.0000

Data Index: 459601 (C4 (Web Text))

Max Activating Token Index: 442

Text #7

Max Range: 0.6371. Min Range: -0.6371

Max Act: 0.4835. Min Act: -0.0000

Data Index: 514492 (C4 (Web Text))

Max Activating Token Index: 725

Text #8

Max Range: 0.6371. Min Range: -0.6371

Max Act: 0.4940. Min Act: -0.0001

Data Index: 246385 (C4 (Web Text))

Max Activating Token Index: 43

Text #9

Max Range: 0.6371. Min Range: -0.6371

Max Act: 0.4886. Min Act: -0.0001

Data Index: 783451 (C4 (Web Text))

Max Activating Token Index: 282

Text #10

Max Range: 0.6371. Min Range: -0.6371

Max Act: 0.4829. Min Act: -0.0000

Data Index: 723078 (C4 (Web Text))

Max Activating Token Index: 182

Text #11

Max Range: 0.6371. Min Range: -0.6371

Max Act: 0.4636. Min Act: -0.0000

Data Index: 479051 (C4 (Web Text))

Max Activating Token Index: 324

Text #12

Max Range: 0.6371. Min Range: -0.6371

Max Act: 0.4568. Min Act: -0.0000

Data Index: 251102 (C4 (Web Text))

Max Activating Token Index: 909

Text #13

Max Range: 0.6371. Min Range: -0.6371

Max Act: 0.4185. Min Act: -0.0000

Data Index: 1155942 (C4 (Web Text))

Max Activating Token Index: 319

Text #14

Max Range: 0.6371. Min Range: -0.6371

Max Act: 0.4240. Min Act: -0.0000

Data Index: 998062 (C4 (Web Text))

Max Activating Token Index: 184

Text #15

Max Range: 0.6371. Min Range: -0.6371

Max Act: 0.4111. Min Act: -0.0000

Data Index: 1195720 (C4 (Web Text))

Max Activating Token Index: 337

Text #16

Max Range: 0.6371. Min Range: -0.6371

Max Act: 0.4096. Min Act: 0.0000

Data Index: 290786 (C4 (Web Text))

Max Activating Token Index: 703

Text #17

Max Range: 0.6371. Min Range: -0.6371

Max Act: 0.3976. Min Act: -0.0000

Data Index: 53317 (C4 (Web Text))

Max Activating Token Index: 254

Text #18

Max Range: 0.6371. Min Range: -0.6371

Max Act: 0.4044. Min Act: -0.0000

Data Index: 561475 (C4 (Web Text))

Max Activating Token Index: 36

Text #19

Max Range: 0.6371. Min Range: -0.6371

Max Act: 0.4152. Min Act: -0.0000

Data Index: 830505 (C4 (Web Text))

Max Activating Token Index: 713