Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 459 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0371. Min Range: -0.0371

Max Act: 0.0359. Min Act: -0.0001

Data Index: 1277811 (C4 (Web Text))

Max Activating Token Index: 979

Text #1

Max Range: 0.0371. Min Range: -0.0371

Max Act: 0.0371. Min Act: -0.0001

Data Index: 171275 (C4 (Web Text))

Max Activating Token Index: 733

Text #2

Max Range: 0.0371. Min Range: -0.0371

Max Act: 0.0364. Min Act: -0.0001

Data Index: 79593 (C4 (Web Text))

Max Activating Token Index: 227

Text #3

Max Range: 0.0371. Min Range: -0.0371

Max Act: 0.0359. Min Act: -0.0001

Data Index: 862384 (C4 (Web Text))

Max Activating Token Index: 410

Text #4

Max Range: 0.0371. Min Range: -0.0371

Max Act: 0.0352. Min Act: -0.0001

Data Index: 1556136 (Python Code)

Max Activating Token Index: 531

Text #5

Max Range: 0.0371. Min Range: -0.0371

Max Act: 0.0345. Min Act: -0.0001

Data Index: 38635 (C4 (Web Text))

Max Activating Token Index: 54

Text #6

Max Range: 0.0371. Min Range: -0.0371

Max Act: 0.0352. Min Act: -0.0001

Data Index: 1052635 (C4 (Web Text))

Max Activating Token Index: 661

Text #7

Max Range: 0.0371. Min Range: -0.0371

Max Act: 0.0320. Min Act: -0.0001

Data Index: 685023 (C4 (Web Text))

Max Activating Token Index: 524

Text #8

Max Range: 0.0371. Min Range: -0.0371

Max Act: 0.0351. Min Act: -0.0001

Data Index: 1013164 (C4 (Web Text))

Max Activating Token Index: 616

Text #9

Max Range: 0.0371. Min Range: -0.0371

Max Act: 0.0302. Min Act: -0.0001

Data Index: 556848 (C4 (Web Text))

Max Activating Token Index: 524

Text #10

Max Range: 0.0371. Min Range: -0.0371

Max Act: 0.0325. Min Act: -0.0001

Data Index: 946061 (C4 (Web Text))

Max Activating Token Index: 667

Text #11

Max Range: 0.0371. Min Range: -0.0371

Max Act: 0.0333. Min Act: -0.0001

Data Index: 265912 (C4 (Web Text))

Max Activating Token Index: 478

Text #12

Max Range: 0.0371. Min Range: -0.0371

Max Act: 0.0314. Min Act: -0.0001

Data Index: 83104 (C4 (Web Text))

Max Activating Token Index: 252

Text #13

Max Range: 0.0371. Min Range: -0.0371

Max Act: 0.0306. Min Act: -0.0001

Data Index: 430762 (C4 (Web Text))

Max Activating Token Index: 759

Text #14

Max Range: 0.0371. Min Range: -0.0371

Max Act: 0.0324. Min Act: -0.0001

Data Index: 1631878 (Python Code)

Max Activating Token Index: 483

Text #15

Max Range: 0.0371. Min Range: -0.0371

Max Act: 0.0309. Min Act: -0.0001

Data Index: 589593 (C4 (Web Text))

Max Activating Token Index: 278

Text #16

Max Range: 0.0371. Min Range: -0.0371

Max Act: 0.0297. Min Act: -0.0001

Data Index: 730945 (C4 (Web Text))

Max Activating Token Index: 913

Text #17

Max Range: 0.0371. Min Range: -0.0371

Max Act: 0.0319. Min Act: -0.0001

Data Index: 613170 (C4 (Web Text))

Max Activating Token Index: 355

Text #18

Max Range: 0.0371. Min Range: -0.0371

Max Act: 0.0317. Min Act: -0.0001

Data Index: 1028742 (C4 (Web Text))

Max Activating Token Index: 620

Text #19

Max Range: 0.0371. Min Range: -0.0371

Max Act: 0.0316. Min Act: -0.0001

Data Index: 642382 (C4 (Web Text))

Max Activating Token Index: 139