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

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

Neuron 4409 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: 0.0462. Min Range: -0.0462

Max Act: 0.0462. Min Act: -0.0003

Data Index: 449141 (C4 (Web Text))

Max Activating Token Index: 267

Text #1

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0460. Min Act: -0.0003

Data Index: 940311 (C4 (Web Text))

Max Activating Token Index: 128

Text #2

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0384. Min Act: -0.0003

Data Index: 887179 (C4 (Web Text))

Max Activating Token Index: 352

Text #3

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0401. Min Act: -0.0003

Data Index: 607402 (C4 (Web Text))

Max Activating Token Index: 913

Text #4

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0377. Min Act: -0.0003

Data Index: 685306 (C4 (Web Text))

Max Activating Token Index: 546

Text #5

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0373. Min Act: -0.0003

Data Index: 14685 (C4 (Web Text))

Max Activating Token Index: 200

Text #6

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0357. Min Act: -0.0002

Data Index: 435344 (C4 (Web Text))

Max Activating Token Index: 706

Text #7

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0356. Min Act: -0.0003

Data Index: 311639 (C4 (Web Text))

Max Activating Token Index: 485

Text #8

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0356. Min Act: -0.0003

Data Index: 121642 (C4 (Web Text))

Max Activating Token Index: 237

Text #9

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0356. Min Act: -0.0003

Data Index: 440958 (C4 (Web Text))

Max Activating Token Index: 771

Text #10

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0355. Min Act: -0.0003

Data Index: 762564 (C4 (Web Text))

Max Activating Token Index: 783

Text #11

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0359. Min Act: -0.0003

Data Index: 622816 (C4 (Web Text))

Max Activating Token Index: 711

Text #12

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0356. Min Act: -0.0003

Data Index: 769099 (C4 (Web Text))

Max Activating Token Index: 477

Text #13

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0350. Min Act: -0.0003

Data Index: 212782 (C4 (Web Text))

Max Activating Token Index: 335

Text #14

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0349. Min Act: -0.0003

Data Index: 1223063 (C4 (Web Text))

Max Activating Token Index: 790

Text #15

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0329. Min Act: -0.0003

Data Index: 1081524 (C4 (Web Text))

Max Activating Token Index: 376

Text #16

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0334. Min Act: -0.0003

Data Index: 1051560 (C4 (Web Text))

Max Activating Token Index: 709

Text #17

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0338. Min Act: -0.0003

Data Index: 492775 (C4 (Web Text))

Max Activating Token Index: 583

Text #18

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0323. Min Act: -0.0003

Data Index: 842904 (C4 (Web Text))

Max Activating Token Index: 890

Text #19

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0324. Min Act: -0.0002

Data Index: 722303 (C4 (Web Text))

Max Activating Token Index: 665