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

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

Neuron 4263 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: 0.0432. Min Range: -0.0432

Max Act: 0.0432. Min Act: -0.0002

Data Index: 535441 (C4 (Web Text))

Max Activating Token Index: 200

Text #1

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0401. Min Act: -0.0002

Data Index: 243046 (C4 (Web Text))

Max Activating Token Index: 763

Text #2

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0390. Min Act: -0.0002

Data Index: 838790 (C4 (Web Text))

Max Activating Token Index: 838

Text #3

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0366. Min Act: -0.0002

Data Index: 26991 (C4 (Web Text))

Max Activating Token Index: 973

Text #4

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0370. Min Act: -0.0002

Data Index: 477120 (C4 (Web Text))

Max Activating Token Index: 871

Text #5

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0362. Min Act: -0.0002

Data Index: 937786 (C4 (Web Text))

Max Activating Token Index: 625

Text #6

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0366. Min Act: -0.0002

Data Index: 1249762 (C4 (Web Text))

Max Activating Token Index: 566

Text #7

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0373. Min Act: -0.0002

Data Index: 271536 (C4 (Web Text))

Max Activating Token Index: 617

Text #8

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0364. Min Act: -0.0002

Data Index: 1282758 (C4 (Web Text))

Max Activating Token Index: 436

Text #9

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0349. Min Act: -0.0002

Data Index: 1259858 (C4 (Web Text))

Max Activating Token Index: 804

Text #10

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0341. Min Act: -0.0002

Data Index: 110204 (C4 (Web Text))

Max Activating Token Index: 234

Text #11

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0347. Min Act: -0.0002

Data Index: 54531 (C4 (Web Text))

Max Activating Token Index: 590

Text #12

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0326. Min Act: -0.0002

Data Index: 857661 (C4 (Web Text))

Max Activating Token Index: 968

Text #13

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0326. Min Act: -0.0002

Data Index: 36576 (C4 (Web Text))

Max Activating Token Index: 475

Text #14

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0330. Min Act: -0.0002

Data Index: 944169 (C4 (Web Text))

Max Activating Token Index: 561

Text #15

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0319. Min Act: -0.0002

Data Index: 865050 (C4 (Web Text))

Max Activating Token Index: 317

Text #16

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0322. Min Act: -0.0002

Data Index: 728639 (C4 (Web Text))

Max Activating Token Index: 996

Text #17

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0316. Min Act: -0.0002

Data Index: 603625 (C4 (Web Text))

Max Activating Token Index: 443

Text #18

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0319. Min Act: -0.0002

Data Index: 541134 (C4 (Web Text))

Max Activating Token Index: 990

Text #19

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0311. Min Act: -0.0002

Data Index: 972550 (C4 (Web Text))

Max Activating Token Index: 174