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

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

Neuron 2668 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: 1.0702. Min Range: -1.0702

Max Act: 1.0702. Min Act: -0.0002

Data Index: 1393950 (Python Code)

Max Activating Token Index: 711

Text #1

Max Range: 1.0702. Min Range: -1.0702

Max Act: 0.9327. Min Act: -0.0002

Data Index: 763823 (C4 (Web Text))

Max Activating Token Index: 285

Text #2

Max Range: 1.0702. Min Range: -1.0702

Max Act: 1.0441. Min Act: -0.0002

Data Index: 1566836 (Python Code)

Max Activating Token Index: 579

Text #3

Max Range: 1.0702. Min Range: -1.0702

Max Act: 0.8981. Min Act: -0.0002

Data Index: 1076844 (C4 (Web Text))

Max Activating Token Index: 71

Text #4

Max Range: 1.0702. Min Range: -1.0702

Max Act: 0.9319. Min Act: -0.0002

Data Index: 1597466 (Python Code)

Max Activating Token Index: 500

Text #5

Max Range: 1.0702. Min Range: -1.0702

Max Act: 0.8118. Min Act: -0.0002

Data Index: 1534449 (Python Code)

Max Activating Token Index: 640

Text #6

Max Range: 1.0702. Min Range: -1.0702

Max Act: 0.9033. Min Act: -0.0002

Data Index: 1599426 (Python Code)

Max Activating Token Index: 26

Text #7

Max Range: 1.0702. Min Range: -1.0702

Max Act: 0.8677. Min Act: -0.0002

Data Index: 1354015 (C4 (Web Text))

Max Activating Token Index: 522

Text #8

Max Range: 1.0702. Min Range: -1.0702

Max Act: 0.8414. Min Act: -0.0002

Data Index: 788271 (C4 (Web Text))

Max Activating Token Index: 878

Text #9

Max Range: 1.0702. Min Range: -1.0702

Max Act: 0.7739. Min Act: -0.0002

Data Index: 533631 (C4 (Web Text))

Max Activating Token Index: 232

Text #10

Max Range: 1.0702. Min Range: -1.0702

Max Act: 0.8121. Min Act: -0.0002

Data Index: 293803 (C4 (Web Text))

Max Activating Token Index: 81

Text #11

Max Range: 1.0702. Min Range: -1.0702

Max Act: 0.8135. Min Act: -0.0002

Data Index: 497400 (C4 (Web Text))

Max Activating Token Index: 44

Text #12

Max Range: 1.0702. Min Range: -1.0702

Max Act: 0.8682. Min Act: -0.0002

Data Index: 1007343 (C4 (Web Text))

Max Activating Token Index: 93

Text #13

Max Range: 1.0702. Min Range: -1.0702

Max Act: 0.9361. Min Act: -0.0002

Data Index: 1368014 (Python Code)

Max Activating Token Index: 596

Text #14

Max Range: 1.0702. Min Range: -1.0702

Max Act: 0.8265. Min Act: -0.0002

Data Index: 440833 (C4 (Web Text))

Max Activating Token Index: 199

Text #15

Max Range: 1.0702. Min Range: -1.0702

Max Act: 0.8265. Min Act: -0.0002

Data Index: 662985 (C4 (Web Text))

Max Activating Token Index: 991

Text #16

Max Range: 1.0702. Min Range: -1.0702

Max Act: 0.8258. Min Act: -0.0002

Data Index: 139824 (C4 (Web Text))

Max Activating Token Index: 55

Text #17

Max Range: 1.0702. Min Range: -1.0702

Max Act: 0.8246. Min Act: -0.0002

Data Index: 166523 (C4 (Web Text))

Max Activating Token Index: 338

Text #18

Max Range: 1.0702. Min Range: -1.0702

Max Act: 0.7469. Min Act: -0.0002

Data Index: 1583670 (Python Code)

Max Activating Token Index: 324

Text #19

Max Range: 1.0702. Min Range: -1.0702

Max Act: 0.8417. Min Act: -0.0002

Data Index: 110560 (C4 (Web Text))

Max Activating Token Index: 476