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

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

Neuron 429 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: 0.2209. Min Range: -0.2209

Max Act: 0.2209. Min Act: -0.0001

Data Index: 1078744 (C4 (Web Text))

Max Activating Token Index: 493

Text #1

Max Range: 0.2209. Min Range: -0.2209

Max Act: 0.2053. Min Act: -0.0001

Data Index: 894202 (C4 (Web Text))

Max Activating Token Index: 607

Text #2

Max Range: 0.2209. Min Range: -0.2209

Max Act: 0.2009. Min Act: -0.0001

Data Index: 365238 (C4 (Web Text))

Max Activating Token Index: 886

Text #3

Max Range: 0.2209. Min Range: -0.2209

Max Act: 0.1978. Min Act: -0.0001

Data Index: 1258458 (C4 (Web Text))

Max Activating Token Index: 766

Text #4

Max Range: 0.2209. Min Range: -0.2209

Max Act: 0.2197. Min Act: -0.0001

Data Index: 777480 (C4 (Web Text))

Max Activating Token Index: 402

Text #5

Max Range: 0.2209. Min Range: -0.2209

Max Act: 0.2120. Min Act: -0.0001

Data Index: 1109426 (C4 (Web Text))

Max Activating Token Index: 439

Text #6

Max Range: 0.2209. Min Range: -0.2209

Max Act: 0.2098. Min Act: -0.0001

Data Index: 483561 (C4 (Web Text))

Max Activating Token Index: 460

Text #7

Max Range: 0.2209. Min Range: -0.2209

Max Act: 0.1670. Min Act: -0.0001

Data Index: 136628 (C4 (Web Text))

Max Activating Token Index: 794

Text #8

Max Range: 0.2209. Min Range: -0.2209

Max Act: 0.1889. Min Act: -0.0001

Data Index: 758304 (C4 (Web Text))

Max Activating Token Index: 757

Text #9

Max Range: 0.2209. Min Range: -0.2209

Max Act: 0.1845. Min Act: -0.0001

Data Index: 649239 (C4 (Web Text))

Max Activating Token Index: 253

Text #10

Max Range: 0.2209. Min Range: -0.2209

Max Act: 0.1741. Min Act: -0.0001

Data Index: 173031 (C4 (Web Text))

Max Activating Token Index: 81

Text #11

Max Range: 0.2209. Min Range: -0.2209

Max Act: 0.1676. Min Act: -0.0001

Data Index: 341246 (C4 (Web Text))

Max Activating Token Index: 965

Text #12

Max Range: 0.2209. Min Range: -0.2209

Max Act: 0.1766. Min Act: -0.0001

Data Index: 1063614 (C4 (Web Text))

Max Activating Token Index: 726

Text #13

Max Range: 0.2209. Min Range: -0.2209

Max Act: 0.1758. Min Act: -0.0001

Data Index: 93327 (C4 (Web Text))

Max Activating Token Index: 978

Text #14

Max Range: 0.2209. Min Range: -0.2209

Max Act: 0.1747. Min Act: -0.0001

Data Index: 880727 (C4 (Web Text))

Max Activating Token Index: 651

Text #15

Max Range: 0.2209. Min Range: -0.2209

Max Act: 0.1742. Min Act: -0.0001

Data Index: 566847 (C4 (Web Text))

Max Activating Token Index: 292

Text #16

Max Range: 0.2209. Min Range: -0.2209

Max Act: 0.1691. Min Act: -0.0001

Data Index: 1251402 (C4 (Web Text))

Max Activating Token Index: 832

Text #17

Max Range: 0.2209. Min Range: -0.2209

Max Act: 0.1630. Min Act: -0.0001

Data Index: 491326 (C4 (Web Text))

Max Activating Token Index: 919

Text #18

Max Range: 0.2209. Min Range: -0.2209

Max Act: 0.1683. Min Act: -0.0001

Data Index: 1191657 (C4 (Web Text))

Max Activating Token Index: 253

Text #19

Max Range: 0.2209. Min Range: -0.2209

Max Act: 0.1707. Min Act: -0.0001

Data Index: 1026916 (C4 (Web Text))

Max Activating Token Index: 598