Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 2016 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0480. Min Act: -0.0006

Data Index: 1320550 (C4 (Web Text))

Max Activating Token Index: 196

Text #1

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0388. Min Act: -0.0006

Data Index: 143699 (C4 (Web Text))

Max Activating Token Index: 821

Text #2

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0409. Min Act: -0.0006

Data Index: 1116779 (C4 (Web Text))

Max Activating Token Index: 793

Text #3

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0397. Min Act: -0.0006

Data Index: 27835 (C4 (Web Text))

Max Activating Token Index: 280

Text #4

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0353. Min Act: -0.0006

Data Index: 648720 (C4 (Web Text))

Max Activating Token Index: 729

Text #5

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0373. Min Act: -0.0006

Data Index: 578541 (C4 (Web Text))

Max Activating Token Index: 230

Text #6

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0371. Min Act: -0.0006

Data Index: 100074 (C4 (Web Text))

Max Activating Token Index: 663

Text #7

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0376. Min Act: -0.0006

Data Index: 568534 (C4 (Web Text))

Max Activating Token Index: 95

Text #8

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0358. Min Act: -0.0006

Data Index: 1307337 (C4 (Web Text))

Max Activating Token Index: 249

Text #9

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0328. Min Act: -0.0006

Data Index: 847401 (C4 (Web Text))

Max Activating Token Index: 327

Text #10

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0347. Min Act: -0.0006

Data Index: 829721 (C4 (Web Text))

Max Activating Token Index: 935

Text #11

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0349. Min Act: -0.0006

Data Index: 240788 (C4 (Web Text))

Max Activating Token Index: 132

Text #12

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0343. Min Act: -0.0006

Data Index: 611564 (C4 (Web Text))

Max Activating Token Index: 124

Text #13

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0342. Min Act: -0.0006

Data Index: 1063668 (C4 (Web Text))

Max Activating Token Index: 848

Text #14

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0334. Min Act: -0.0006

Data Index: 1001664 (C4 (Web Text))

Max Activating Token Index: 327

Text #15

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0332. Min Act: -0.0006

Data Index: 202152 (C4 (Web Text))

Max Activating Token Index: 826

Text #16

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0309. Min Act: -0.0006

Data Index: 466077 (C4 (Web Text))

Max Activating Token Index: 307

Text #17

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0338. Min Act: -0.0006

Data Index: 1043044 (C4 (Web Text))

Max Activating Token Index: 379

Text #18

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0346. Min Act: -0.0006

Data Index: 1322607 (C4 (Web Text))

Max Activating Token Index: 465

Text #19

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0324. Min Act: -0.0006

Data Index: 719676 (C4 (Web Text))

Max Activating Token Index: 264