Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 833 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2534. Min Range: -0.2534

Max Act: 0.2532. Min Act: -0.0001

Data Index: 415218 (C4 (Web Text))

Max Activating Token Index: 638

Text #1

Max Range: 0.2534. Min Range: -0.2534

Max Act: 0.2534. Min Act: -0.0001

Data Index: 314646 (C4 (Web Text))

Max Activating Token Index: 151

Text #2

Max Range: 0.2534. Min Range: -0.2534

Max Act: 0.2140. Min Act: -0.0001

Data Index: 743691 (C4 (Web Text))

Max Activating Token Index: 422

Text #3

Max Range: 0.2534. Min Range: -0.2534

Max Act: 0.2191. Min Act: -0.0001

Data Index: 277807 (C4 (Web Text))

Max Activating Token Index: 697

Text #4

Max Range: 0.2534. Min Range: -0.2534

Max Act: 0.2264. Min Act: -0.0001

Data Index: 394679 (C4 (Web Text))

Max Activating Token Index: 466

Text #5

Max Range: 0.2534. Min Range: -0.2534

Max Act: 0.2235. Min Act: -0.0001

Data Index: 1019874 (C4 (Web Text))

Max Activating Token Index: 422

Text #6

Max Range: 0.2534. Min Range: -0.2534

Max Act: 0.2115. Min Act: -0.0001

Data Index: 338546 (C4 (Web Text))

Max Activating Token Index: 882

Text #7

Max Range: 0.2534. Min Range: -0.2534

Max Act: 0.2260. Min Act: -0.0001

Data Index: 633574 (C4 (Web Text))

Max Activating Token Index: 132

Text #8

Max Range: 0.2534. Min Range: -0.2534

Max Act: 0.2155. Min Act: -0.0001

Data Index: 816797 (C4 (Web Text))

Max Activating Token Index: 98

Text #9

Max Range: 0.2534. Min Range: -0.2534

Max Act: 0.2076. Min Act: -0.0001

Data Index: 3531 (C4 (Web Text))

Max Activating Token Index: 141

Text #10

Max Range: 0.2534. Min Range: -0.2534

Max Act: 0.2083. Min Act: -0.0001

Data Index: 447080 (C4 (Web Text))

Max Activating Token Index: 763

Text #11

Max Range: 0.2534. Min Range: -0.2534

Max Act: 0.1928. Min Act: -0.0001

Data Index: 526964 (C4 (Web Text))

Max Activating Token Index: 1014

Text #12

Max Range: 0.2534. Min Range: -0.2534

Max Act: 0.1938. Min Act: -0.0001

Data Index: 858408 (C4 (Web Text))

Max Activating Token Index: 797

Text #13

Max Range: 0.2534. Min Range: -0.2534

Max Act: 0.1971. Min Act: -0.0001

Data Index: 422941 (C4 (Web Text))

Max Activating Token Index: 451

Text #14

Max Range: 0.2534. Min Range: -0.2534

Max Act: 0.1981. Min Act: -0.0001

Data Index: 750102 (C4 (Web Text))

Max Activating Token Index: 265

Text #15

Max Range: 0.2534. Min Range: -0.2534

Max Act: 0.1960. Min Act: -0.0001

Data Index: 1037787 (C4 (Web Text))

Max Activating Token Index: 579

Text #16

Max Range: 0.2534. Min Range: -0.2534

Max Act: 0.1791. Min Act: -0.0001

Data Index: 94984 (C4 (Web Text))

Max Activating Token Index: 203

Text #17

Max Range: 0.2534. Min Range: -0.2534

Max Act: 0.1967. Min Act: -0.0001

Data Index: 142437 (C4 (Web Text))

Max Activating Token Index: 739

Text #18

Max Range: 0.2534. Min Range: -0.2534

Max Act: 0.1835. Min Act: -0.0001

Data Index: 86843 (C4 (Web Text))

Max Activating Token Index: 140

Text #19

Max Range: 0.2534. Min Range: -0.2534

Max Act: 0.1823. Min Act: -0.0001

Data Index: 135673 (C4 (Web Text))

Max Activating Token Index: 72