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

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

Neuron 3751 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0496. Min Act: -0.0001

Data Index: 665037 (C4 (Web Text))

Max Activating Token Index: 418

Text #1

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0429. Min Act: -0.0002

Data Index: 626570 (C4 (Web Text))

Max Activating Token Index: 198

Text #2

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0449. Min Act: -0.0002

Data Index: 1110462 (C4 (Web Text))

Max Activating Token Index: 577

Text #3

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0417. Min Act: -0.0001

Data Index: 1562178 (Python Code)

Max Activating Token Index: 872

Text #4

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0420. Min Act: -0.0001

Data Index: 1334393 (C4 (Web Text))

Max Activating Token Index: 711

Text #5

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0423. Min Act: -0.0002

Data Index: 1175631 (C4 (Web Text))

Max Activating Token Index: 738

Text #6

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0347. Min Act: -0.0001

Data Index: 1532251 (Python Code)

Max Activating Token Index: 662

Text #7

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0385. Min Act: -0.0002

Data Index: 619855 (C4 (Web Text))

Max Activating Token Index: 3

Text #8

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0349. Min Act: -0.0001

Data Index: 721555 (C4 (Web Text))

Max Activating Token Index: 650

Text #9

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0360. Min Act: -0.0002

Data Index: 1067602 (C4 (Web Text))

Max Activating Token Index: 18

Text #10

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0375. Min Act: -0.0001

Data Index: 1017163 (C4 (Web Text))

Max Activating Token Index: 878

Text #11

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0371. Min Act: -0.0001

Data Index: 194712 (C4 (Web Text))

Max Activating Token Index: 851

Text #12

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0353. Min Act: -0.0002

Data Index: 371289 (C4 (Web Text))

Max Activating Token Index: 595

Text #13

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0344. Min Act: -0.0002

Data Index: 534753 (C4 (Web Text))

Max Activating Token Index: 889

Text #14

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0359. Min Act: -0.0001

Data Index: 248050 (C4 (Web Text))

Max Activating Token Index: 570

Text #15

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0346. Min Act: -0.0001

Data Index: 1224832 (C4 (Web Text))

Max Activating Token Index: 949

Text #16

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0332. Min Act: -0.0001

Data Index: 1046138 (C4 (Web Text))

Max Activating Token Index: 833

Text #17

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0373. Min Act: -0.0002

Data Index: 705602 (C4 (Web Text))

Max Activating Token Index: 608

Text #18

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0365. Min Act: -0.0002

Data Index: 950948 (C4 (Web Text))

Max Activating Token Index: 861

Text #19

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0327. Min Act: -0.0001

Data Index: 725806 (C4 (Web Text))

Max Activating Token Index: 935