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

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

Neuron 4503 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5878. Min Range: -1.5878

Max Act: 1.5878. Min Act: -0.0001

Data Index: 451648 (C4 (Web Text))

Max Activating Token Index: 15

Text #1

Max Range: 1.5878. Min Range: -1.5878

Max Act: 1.4383. Min Act: -0.0001

Data Index: 938015 (C4 (Web Text))

Max Activating Token Index: 163

Text #2

Max Range: 1.5878. Min Range: -1.5878

Max Act: 1.3475. Min Act: -0.0001

Data Index: 434707 (C4 (Web Text))

Max Activating Token Index: 37

Text #3

Max Range: 1.5878. Min Range: -1.5878

Max Act: 1.1707. Min Act: -0.0001

Data Index: 254621 (C4 (Web Text))

Max Activating Token Index: 545

Text #4

Max Range: 1.5878. Min Range: -1.5878

Max Act: 1.1619. Min Act: -0.0001

Data Index: 618802 (C4 (Web Text))

Max Activating Token Index: 24

Text #5

Max Range: 1.5878. Min Range: -1.5878

Max Act: 1.0472. Min Act: -0.0001

Data Index: 1199823 (C4 (Web Text))

Max Activating Token Index: 479

Text #6

Max Range: 1.5878. Min Range: -1.5878

Max Act: 1.1319. Min Act: -0.0000

Data Index: 175309 (C4 (Web Text))

Max Activating Token Index: 261

Text #7

Max Range: 1.5878. Min Range: -1.5878

Max Act: 1.1491. Min Act: -0.0001

Data Index: 1135055 (C4 (Web Text))

Max Activating Token Index: 698

Text #8

Max Range: 1.5878. Min Range: -1.5878

Max Act: 1.0040. Min Act: -0.0001

Data Index: 946979 (C4 (Web Text))

Max Activating Token Index: 811

Text #9

Max Range: 1.5878. Min Range: -1.5878

Max Act: 1.0380. Min Act: -0.0001

Data Index: 1105501 (C4 (Web Text))

Max Activating Token Index: 361

Text #10

Max Range: 1.5878. Min Range: -1.5878

Max Act: 1.0349. Min Act: -0.0000

Data Index: 245056 (C4 (Web Text))

Max Activating Token Index: 84

Text #11

Max Range: 1.5878. Min Range: -1.5878

Max Act: 0.9708. Min Act: -0.0001

Data Index: 743308 (C4 (Web Text))

Max Activating Token Index: 262

Text #12

Max Range: 1.5878. Min Range: -1.5878

Max Act: 1.0683. Min Act: -0.0001

Data Index: 842531 (C4 (Web Text))

Max Activating Token Index: 911

Text #13

Max Range: 1.5878. Min Range: -1.5878

Max Act: 1.0219. Min Act: -0.0001

Data Index: 342588 (C4 (Web Text))

Max Activating Token Index: 7

Text #14

Max Range: 1.5878. Min Range: -1.5878

Max Act: 0.9459. Min Act: -0.0001

Data Index: 787363 (C4 (Web Text))

Max Activating Token Index: 587

Text #15

Max Range: 1.5878. Min Range: -1.5878

Max Act: 0.9446. Min Act: -0.0001

Data Index: 455267 (C4 (Web Text))

Max Activating Token Index: 626

Text #16

Max Range: 1.5878. Min Range: -1.5878

Max Act: 0.9641. Min Act: -0.0001

Data Index: 873814 (C4 (Web Text))

Max Activating Token Index: 117

Text #17

Max Range: 1.5878. Min Range: -1.5878

Max Act: 1.0144. Min Act: -0.0001

Data Index: 1269868 (C4 (Web Text))

Max Activating Token Index: 318

Text #18

Max Range: 1.5878. Min Range: -1.5878

Max Act: 1.0460. Min Act: -0.0000

Data Index: 676399 (C4 (Web Text))

Max Activating Token Index: 8

Text #19

Max Range: 1.5878. Min Range: -1.5878

Max Act: 1.0402. Min Act: -0.0001

Data Index: 1075668 (C4 (Web Text))

Max Activating Token Index: 920