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

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

Neuron 3998 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.3253. Min Range: -1.3253

Max Act: 1.1997. Min Act: -0.0001

Data Index: 998907 (C4 (Web Text))

Max Activating Token Index: 1022

Text #1

Max Range: 1.3253. Min Range: -1.3253

Max Act: 1.1702. Min Act: -0.0001

Data Index: 233408 (C4 (Web Text))

Max Activating Token Index: 65

Text #2

Max Range: 1.3253. Min Range: -1.3253

Max Act: 1.2747. Min Act: -0.0001

Data Index: 525541 (C4 (Web Text))

Max Activating Token Index: 155

Text #3

Max Range: 1.3253. Min Range: -1.3253

Max Act: 1.3029. Min Act: -0.0001

Data Index: 476469 (C4 (Web Text))

Max Activating Token Index: 489

Text #4

Max Range: 1.3253. Min Range: -1.3253

Max Act: 1.2487. Min Act: -0.0001

Data Index: 858442 (C4 (Web Text))

Max Activating Token Index: 398

Text #5

Max Range: 1.3253. Min Range: -1.3253

Max Act: 1.3253. Min Act: -0.0001

Data Index: 918911 (C4 (Web Text))

Max Activating Token Index: 278

Text #6

Max Range: 1.3253. Min Range: -1.3253

Max Act: 1.0500. Min Act: -0.0001

Data Index: 988835 (C4 (Web Text))

Max Activating Token Index: 154

Text #7

Max Range: 1.3253. Min Range: -1.3253

Max Act: 1.2673. Min Act: -0.0001

Data Index: 121764 (C4 (Web Text))

Max Activating Token Index: 433

Text #8

Max Range: 1.3253. Min Range: -1.3253

Max Act: 1.2522. Min Act: -0.0001

Data Index: 1262993 (C4 (Web Text))

Max Activating Token Index: 369

Text #9

Max Range: 1.3253. Min Range: -1.3253

Max Act: 1.1124. Min Act: -0.0001

Data Index: 113594 (C4 (Web Text))

Max Activating Token Index: 795

Text #10

Max Range: 1.3253. Min Range: -1.3253

Max Act: 1.0801. Min Act: -0.0001

Data Index: 766638 (C4 (Web Text))

Max Activating Token Index: 817

Text #11

Max Range: 1.3253. Min Range: -1.3253

Max Act: 1.0341. Min Act: -0.0001

Data Index: 48937 (C4 (Web Text))

Max Activating Token Index: 693

Text #12

Max Range: 1.3253. Min Range: -1.3253

Max Act: 1.1369. Min Act: -0.0001

Data Index: 866520 (C4 (Web Text))

Max Activating Token Index: 89

Text #13

Max Range: 1.3253. Min Range: -1.3253

Max Act: 1.0959. Min Act: -0.0001

Data Index: 1158961 (C4 (Web Text))

Max Activating Token Index: 813

Text #14

Max Range: 1.3253. Min Range: -1.3253

Max Act: 1.0726. Min Act: -0.0001

Data Index: 631555 (C4 (Web Text))

Max Activating Token Index: 634

Text #15

Max Range: 1.3253. Min Range: -1.3253

Max Act: 1.0783. Min Act: -0.0001

Data Index: 286658 (C4 (Web Text))

Max Activating Token Index: 526

Text #16

Max Range: 1.3253. Min Range: -1.3253

Max Act: 1.2326. Min Act: -0.0001

Data Index: 1289691 (C4 (Web Text))

Max Activating Token Index: 133

Text #17

Max Range: 1.3253. Min Range: -1.3253

Max Act: 1.1376. Min Act: -0.0001

Data Index: 1241553 (C4 (Web Text))

Max Activating Token Index: 796

Text #18

Max Range: 1.3253. Min Range: -1.3253

Max Act: 1.3041. Min Act: -0.0001

Data Index: 881417 (C4 (Web Text))

Max Activating Token Index: 875

Text #19

Max Range: 1.3253. Min Range: -1.3253

Max Act: 1.1226. Min Act: -0.0001

Data Index: 403444 (C4 (Web Text))

Max Activating Token Index: 154