Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2589 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.4313. Min Range: -0.4313

Max Act: 0.4313. Min Act: -0.0001

Data Index: 602479 (C4 (Web Text))

Max Activating Token Index: 711

Text #1

Max Range: 0.4313. Min Range: -0.4313

Max Act: 0.4117. Min Act: -0.0001

Data Index: 863718 (C4 (Web Text))

Max Activating Token Index: 58

Text #2

Max Range: 0.4313. Min Range: -0.4313

Max Act: 0.3858. Min Act: -0.0001

Data Index: 1303419 (C4 (Web Text))

Max Activating Token Index: 630

Text #3

Max Range: 0.4313. Min Range: -0.4313

Max Act: 0.3716. Min Act: -0.0001

Data Index: 159224 (C4 (Web Text))

Max Activating Token Index: 68

Text #4

Max Range: 0.4313. Min Range: -0.4313

Max Act: 0.3453. Min Act: -0.0001

Data Index: 225997 (C4 (Web Text))

Max Activating Token Index: 486

Text #5

Max Range: 0.4313. Min Range: -0.4313

Max Act: 0.3439. Min Act: -0.0001

Data Index: 1172397 (C4 (Web Text))

Max Activating Token Index: 848

Text #6

Max Range: 0.4313. Min Range: -0.4313

Max Act: 0.3661. Min Act: -0.0001

Data Index: 878651 (C4 (Web Text))

Max Activating Token Index: 444

Text #7

Max Range: 0.4313. Min Range: -0.4313

Max Act: 0.3320. Min Act: -0.0001

Data Index: 1235604 (C4 (Web Text))

Max Activating Token Index: 743

Text #8

Max Range: 0.4313. Min Range: -0.4313

Max Act: 0.3175. Min Act: -0.0001

Data Index: 1070468 (C4 (Web Text))

Max Activating Token Index: 261

Text #9

Max Range: 0.4313. Min Range: -0.4313

Max Act: 0.3283. Min Act: -0.0001

Data Index: 405911 (C4 (Web Text))

Max Activating Token Index: 81

Text #10

Max Range: 0.4313. Min Range: -0.4313

Max Act: 0.3246. Min Act: -0.0001

Data Index: 1168611 (C4 (Web Text))

Max Activating Token Index: 664

Text #11

Max Range: 0.4313. Min Range: -0.4313

Max Act: 0.3159. Min Act: -0.0000

Data Index: 622496 (C4 (Web Text))

Max Activating Token Index: 83

Text #12

Max Range: 0.4313. Min Range: -0.4313

Max Act: 0.3136. Min Act: -0.0000

Data Index: 655093 (C4 (Web Text))

Max Activating Token Index: 129

Text #13

Max Range: 0.4313. Min Range: -0.4313

Max Act: 0.3422. Min Act: -0.0001

Data Index: 994089 (C4 (Web Text))

Max Activating Token Index: 773

Text #14

Max Range: 0.4313. Min Range: -0.4313

Max Act: 0.3421. Min Act: -0.0001

Data Index: 493760 (C4 (Web Text))

Max Activating Token Index: 546

Text #15

Max Range: 0.4313. Min Range: -0.4313

Max Act: 0.2854. Min Act: -0.0001

Data Index: 1121653 (C4 (Web Text))

Max Activating Token Index: 604

Text #16

Max Range: 0.4313. Min Range: -0.4313

Max Act: 0.3234. Min Act: -0.0001

Data Index: 1149855 (C4 (Web Text))

Max Activating Token Index: 338

Text #17

Max Range: 0.4313. Min Range: -0.4313

Max Act: 0.3249. Min Act: -0.0001

Data Index: 558630 (C4 (Web Text))

Max Activating Token Index: 78

Text #18

Max Range: 0.4313. Min Range: -0.4313

Max Act: 0.3031. Min Act: -0.0001

Data Index: 952733 (C4 (Web Text))

Max Activating Token Index: 809

Text #19

Max Range: 0.4313. Min Range: -0.4313

Max Act: 0.3213. Min Act: -0.0001

Data Index: 842774 (C4 (Web Text))

Max Activating Token Index: 675