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

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

Neuron 2825 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: 1.3605. Min Range: -1.3605

Max Act: 1.3605. Min Act: -0.0000

Data Index: 1397365 (Python Code)

Max Activating Token Index: 460

Text #1

Max Range: 1.3605. Min Range: -1.3605

Max Act: 1.1491. Min Act: -0.0000

Data Index: 718130 (C4 (Web Text))

Max Activating Token Index: 650

Text #2

Max Range: 1.3605. Min Range: -1.3605

Max Act: 1.2676. Min Act: -0.0000

Data Index: 721175 (C4 (Web Text))

Max Activating Token Index: 114

Text #3

Max Range: 1.3605. Min Range: -1.3605

Max Act: 1.1526. Min Act: -0.0000

Data Index: 1134773 (C4 (Web Text))

Max Activating Token Index: 246

Text #4

Max Range: 1.3605. Min Range: -1.3605

Max Act: 1.2427. Min Act: -0.0000

Data Index: 932102 (C4 (Web Text))

Max Activating Token Index: 314

Text #5

Max Range: 1.3605. Min Range: -1.3605

Max Act: 1.2047. Min Act: -0.0000

Data Index: 826858 (C4 (Web Text))

Max Activating Token Index: 261

Text #6

Max Range: 1.3605. Min Range: -1.3605

Max Act: 1.3305. Min Act: -0.0000

Data Index: 614754 (C4 (Web Text))

Max Activating Token Index: 977

Text #7

Max Range: 1.3605. Min Range: -1.3605

Max Act: 1.1399. Min Act: -0.0000

Data Index: 917026 (C4 (Web Text))

Max Activating Token Index: 435

Text #8

Max Range: 1.3605. Min Range: -1.3605

Max Act: 1.2052. Min Act: -0.0000

Data Index: 121460 (C4 (Web Text))

Max Activating Token Index: 561

Text #9

Max Range: 1.3605. Min Range: -1.3605

Max Act: 1.2009. Min Act: -0.0000

Data Index: 119930 (C4 (Web Text))

Max Activating Token Index: 502

Text #10

Max Range: 1.3605. Min Range: -1.3605

Max Act: 1.1985. Min Act: -0.0000

Data Index: 1169830 (C4 (Web Text))

Max Activating Token Index: 175

Text #11

Max Range: 1.3605. Min Range: -1.3605

Max Act: 1.1520. Min Act: -0.0000

Data Index: 1500717 (Python Code)

Max Activating Token Index: 576

Text #12

Max Range: 1.3605. Min Range: -1.3605

Max Act: 1.1563. Min Act: -0.0000

Data Index: 1405933 (Python Code)

Max Activating Token Index: 1018

Text #13

Max Range: 1.3605. Min Range: -1.3605

Max Act: 1.2059. Min Act: -0.0000

Data Index: 294554 (C4 (Web Text))

Max Activating Token Index: 282

Text #14

Max Range: 1.3605. Min Range: -1.3605

Max Act: 1.1728. Min Act: -0.0000

Data Index: 444930 (C4 (Web Text))

Max Activating Token Index: 372

Text #15

Max Range: 1.3605. Min Range: -1.3605

Max Act: 1.1442. Min Act: -0.0000

Data Index: 1058430 (C4 (Web Text))

Max Activating Token Index: 250

Text #16

Max Range: 1.3605. Min Range: -1.3605

Max Act: 1.2437. Min Act: -0.0000

Data Index: 1191829 (C4 (Web Text))

Max Activating Token Index: 263

Text #17

Max Range: 1.3605. Min Range: -1.3605

Max Act: 1.1391. Min Act: -0.0000

Data Index: 181039 (C4 (Web Text))

Max Activating Token Index: 623

Text #18

Max Range: 1.3605. Min Range: -1.3605

Max Act: 1.0378. Min Act: -0.0000

Data Index: 854194 (C4 (Web Text))

Max Activating Token Index: 861

Text #19

Max Range: 1.3605. Min Range: -1.3605

Max Act: 1.0300. Min Act: -0.0000

Data Index: 130236 (C4 (Web Text))

Max Activating Token Index: 417