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

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

Neuron 1968 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0579. Min Act: -0.0003

Data Index: 700831 (C4 (Web Text))

Max Activating Token Index: 262

Text #1

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0547. Min Act: -0.0003

Data Index: 286701 (C4 (Web Text))

Max Activating Token Index: 462

Text #2

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0494. Min Act: -0.0003

Data Index: 1349958 (C4 (Web Text))

Max Activating Token Index: 521

Text #3

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0457. Min Act: -0.0003

Data Index: 516151 (C4 (Web Text))

Max Activating Token Index: 548

Text #4

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0463. Min Act: -0.0003

Data Index: 583331 (C4 (Web Text))

Max Activating Token Index: 29

Text #5

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0468. Min Act: -0.0003

Data Index: 1179292 (C4 (Web Text))

Max Activating Token Index: 224

Text #6

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0449. Min Act: -0.0003

Data Index: 140430 (C4 (Web Text))

Max Activating Token Index: 300

Text #7

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0420. Min Act: -0.0003

Data Index: 530258 (C4 (Web Text))

Max Activating Token Index: 170

Text #8

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0400. Min Act: -0.0003

Data Index: 1019030 (C4 (Web Text))

Max Activating Token Index: 359

Text #9

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0389. Min Act: -0.0003

Data Index: 542055 (C4 (Web Text))

Max Activating Token Index: 636

Text #10

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0404. Min Act: -0.0003

Data Index: 600093 (C4 (Web Text))

Max Activating Token Index: 156

Text #11

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0399. Min Act: -0.0003

Data Index: 1153293 (C4 (Web Text))

Max Activating Token Index: 720

Text #12

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0381. Min Act: -0.0003

Data Index: 398307 (C4 (Web Text))

Max Activating Token Index: 220

Text #13

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0382. Min Act: -0.0003

Data Index: 730828 (C4 (Web Text))

Max Activating Token Index: 278

Text #14

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0375. Min Act: -0.0003

Data Index: 559327 (C4 (Web Text))

Max Activating Token Index: 705

Text #15

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0377. Min Act: -0.0003

Data Index: 484316 (C4 (Web Text))

Max Activating Token Index: 462

Text #16

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0359. Min Act: -0.0003

Data Index: 870080 (C4 (Web Text))

Max Activating Token Index: 437

Text #17

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0363. Min Act: -0.0003

Data Index: 81705 (C4 (Web Text))

Max Activating Token Index: 612

Text #18

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0362. Min Act: -0.0003

Data Index: 864104 (C4 (Web Text))

Max Activating Token Index: 51

Text #19

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0359. Min Act: -0.0002

Data Index: 699928 (C4 (Web Text))

Max Activating Token Index: 655