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

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

Neuron 107 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6152. Min Range: -1.6152

Max Act: 1.6152. Min Act: -0.0000

Data Index: 1358089 (C4 (Web Text))

Max Activating Token Index: 48

Text #1

Max Range: 1.6152. Min Range: -1.6152

Max Act: 1.4327. Min Act: -0.0000

Data Index: 899919 (C4 (Web Text))

Max Activating Token Index: 292

Text #2

Max Range: 1.6152. Min Range: -1.6152

Max Act: 1.4097. Min Act: -0.0000

Data Index: 1226153 (C4 (Web Text))

Max Activating Token Index: 57

Text #3

Max Range: 1.6152. Min Range: -1.6152

Max Act: 1.4617. Min Act: -0.0000

Data Index: 440897 (C4 (Web Text))

Max Activating Token Index: 199

Text #4

Max Range: 1.6152. Min Range: -1.6152

Max Act: 1.3751. Min Act: -0.0000

Data Index: 1008241 (C4 (Web Text))

Max Activating Token Index: 338

Text #5

Max Range: 1.6152. Min Range: -1.6152

Max Act: 1.3052. Min Act: -0.0000

Data Index: 879107 (C4 (Web Text))

Max Activating Token Index: 92

Text #6

Max Range: 1.6152. Min Range: -1.6152

Max Act: 1.4873. Min Act: -0.0000

Data Index: 122469 (C4 (Web Text))

Max Activating Token Index: 562

Text #7

Max Range: 1.6152. Min Range: -1.6152

Max Act: 1.4217. Min Act: -0.0000

Data Index: 1138488 (C4 (Web Text))

Max Activating Token Index: 466

Text #8

Max Range: 1.6152. Min Range: -1.6152

Max Act: 1.2918. Min Act: -0.0000

Data Index: 250162 (C4 (Web Text))

Max Activating Token Index: 37

Text #9

Max Range: 1.6152. Min Range: -1.6152

Max Act: 1.2546. Min Act: -0.0000

Data Index: 1020271 (C4 (Web Text))

Max Activating Token Index: 317

Text #10

Max Range: 1.6152. Min Range: -1.6152

Max Act: 1.2141. Min Act: -0.0000

Data Index: 272468 (C4 (Web Text))

Max Activating Token Index: 719

Text #11

Max Range: 1.6152. Min Range: -1.6152

Max Act: 1.1838. Min Act: -0.0000

Data Index: 730478 (C4 (Web Text))

Max Activating Token Index: 741

Text #12

Max Range: 1.6152. Min Range: -1.6152

Max Act: 1.2702. Min Act: -0.0000

Data Index: 376449 (C4 (Web Text))

Max Activating Token Index: 158

Text #13

Max Range: 1.6152. Min Range: -1.6152

Max Act: 1.2272. Min Act: -0.0000

Data Index: 888165 (C4 (Web Text))

Max Activating Token Index: 573

Text #14

Max Range: 1.6152. Min Range: -1.6152

Max Act: 1.1721. Min Act: -0.0000

Data Index: 1296886 (C4 (Web Text))

Max Activating Token Index: 218

Text #15

Max Range: 1.6152. Min Range: -1.6152

Max Act: 1.2458. Min Act: -0.0000

Data Index: 1260607 (C4 (Web Text))

Max Activating Token Index: 810

Text #16

Max Range: 1.6152. Min Range: -1.6152

Max Act: 1.1893. Min Act: -0.0000

Data Index: 19351 (C4 (Web Text))

Max Activating Token Index: 123

Text #17

Max Range: 1.6152. Min Range: -1.6152

Max Act: 1.2412. Min Act: -0.0000

Data Index: 1053521 (C4 (Web Text))

Max Activating Token Index: 606

Text #18

Max Range: 1.6152. Min Range: -1.6152

Max Act: 1.2407. Min Act: -0.0000

Data Index: 298660 (C4 (Web Text))

Max Activating Token Index: 705

Text #19

Max Range: 1.6152. Min Range: -1.6152

Max Act: 1.2816. Min Act: -0.0000

Data Index: 1075542 (C4 (Web Text))

Max Activating Token Index: 351