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

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

Neuron 4393 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: 0.3649. Min Range: -0.3649

Max Act: 0.3649. Min Act: -0.0003

Data Index: 396666 (C4 (Web Text))

Max Activating Token Index: 402

Text #1

Max Range: 0.3649. Min Range: -0.3649

Max Act: 0.3381. Min Act: -0.0003

Data Index: 649954 (C4 (Web Text))

Max Activating Token Index: 854

Text #2

Max Range: 0.3649. Min Range: -0.3649

Max Act: 0.3024. Min Act: -0.0003

Data Index: 1101950 (C4 (Web Text))

Max Activating Token Index: 402

Text #3

Max Range: 0.3649. Min Range: -0.3649

Max Act: 0.2956. Min Act: -0.0003

Data Index: 561358 (C4 (Web Text))

Max Activating Token Index: 837

Text #4

Max Range: 0.3649. Min Range: -0.3649

Max Act: 0.2747. Min Act: -0.0003

Data Index: 293256 (C4 (Web Text))

Max Activating Token Index: 279

Text #5

Max Range: 0.3649. Min Range: -0.3649

Max Act: 0.2818. Min Act: -0.0003

Data Index: 1030796 (C4 (Web Text))

Max Activating Token Index: 265

Text #6

Max Range: 0.3649. Min Range: -0.3649

Max Act: 0.2803. Min Act: -0.0003

Data Index: 1033942 (C4 (Web Text))

Max Activating Token Index: 676

Text #7

Max Range: 0.3649. Min Range: -0.3649

Max Act: 0.2623. Min Act: -0.0003

Data Index: 1084910 (C4 (Web Text))

Max Activating Token Index: 537

Text #8

Max Range: 0.3649. Min Range: -0.3649

Max Act: 0.2627. Min Act: -0.0003

Data Index: 226875 (C4 (Web Text))

Max Activating Token Index: 304

Text #9

Max Range: 0.3649. Min Range: -0.3649

Max Act: 0.2564. Min Act: -0.0003

Data Index: 1256411 (C4 (Web Text))

Max Activating Token Index: 677

Text #10

Max Range: 0.3649. Min Range: -0.3649

Max Act: 0.2553. Min Act: -0.0003

Data Index: 390682 (C4 (Web Text))

Max Activating Token Index: 804

Text #11

Max Range: 0.3649. Min Range: -0.3649

Max Act: 0.2443. Min Act: -0.0003

Data Index: 479254 (C4 (Web Text))

Max Activating Token Index: 558

Text #12

Max Range: 0.3649. Min Range: -0.3649

Max Act: 0.2438. Min Act: -0.0003

Data Index: 562514 (C4 (Web Text))

Max Activating Token Index: 879

Text #13

Max Range: 0.3649. Min Range: -0.3649

Max Act: 0.2428. Min Act: -0.0003

Data Index: 686024 (C4 (Web Text))

Max Activating Token Index: 106

Text #14

Max Range: 0.3649. Min Range: -0.3649

Max Act: 0.2414. Min Act: -0.0003

Data Index: 319058 (C4 (Web Text))

Max Activating Token Index: 689

Text #15

Max Range: 0.3649. Min Range: -0.3649

Max Act: 0.2391. Min Act: -0.0003

Data Index: 675929 (C4 (Web Text))

Max Activating Token Index: 391

Text #16

Max Range: 0.3649. Min Range: -0.3649

Max Act: 0.2369. Min Act: -0.0003

Data Index: 524025 (C4 (Web Text))

Max Activating Token Index: 685

Text #17

Max Range: 0.3649. Min Range: -0.3649

Max Act: 0.2238. Min Act: -0.0003

Data Index: 1008403 (C4 (Web Text))

Max Activating Token Index: 192

Text #18

Max Range: 0.3649. Min Range: -0.3649

Max Act: 0.2326. Min Act: -0.0002

Data Index: 275032 (C4 (Web Text))

Max Activating Token Index: 530

Text #19

Max Range: 0.3649. Min Range: -0.3649

Max Act: 0.2327. Min Act: -0.0002

Data Index: 1127130 (C4 (Web Text))

Max Activating Token Index: 867