Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 469 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.3620. Min Range: -1.3620

Max Act: 1.3620. Min Act: -0.0000

Data Index: 246755 (C4 (Web Text))

Max Activating Token Index: 298

Text #1

Max Range: 1.3620. Min Range: -1.3620

Max Act: 0.2182. Min Act: 0.0000

Data Index: 118413 (C4 (Web Text))

Max Activating Token Index: 820

Text #2

Max Range: 1.3620. Min Range: -1.3620

Max Act: 0.2263. Min Act: -0.0000

Data Index: 46360 (C4 (Web Text))

Max Activating Token Index: 204

Text #3

Max Range: 1.3620. Min Range: -1.3620

Max Act: 0.2294. Min Act: 0.0000

Data Index: 1100455 (C4 (Web Text))

Max Activating Token Index: 916

Text #4

Max Range: 1.3620. Min Range: -1.3620

Max Act: 0.1967. Min Act: -0.0000

Data Index: 672738 (C4 (Web Text))

Max Activating Token Index: 451

Text #5

Max Range: 1.3620. Min Range: -1.3620

Max Act: 0.2016. Min Act: 0.0000

Data Index: 1094496 (C4 (Web Text))

Max Activating Token Index: 407

Text #6

Max Range: 1.3620. Min Range: -1.3620

Max Act: 0.2082. Min Act: 0.0000

Data Index: 228534 (C4 (Web Text))

Max Activating Token Index: 1012

Text #7

Max Range: 1.3620. Min Range: -1.3620

Max Act: 0.2015. Min Act: 0.0000

Data Index: 115632 (C4 (Web Text))

Max Activating Token Index: 462

Text #8

Max Range: 1.3620. Min Range: -1.3620

Max Act: 0.2144. Min Act: 0.0000

Data Index: 82348 (C4 (Web Text))

Max Activating Token Index: 889

Text #9

Max Range: 1.3620. Min Range: -1.3620

Max Act: 0.1985. Min Act: 0.0000

Data Index: 1071265 (C4 (Web Text))

Max Activating Token Index: 356

Text #10

Max Range: 1.3620. Min Range: -1.3620

Max Act: 0.1944. Min Act: 0.0000

Data Index: 915422 (C4 (Web Text))

Max Activating Token Index: 532

Text #11

Max Range: 1.3620. Min Range: -1.3620

Max Act: 0.2089. Min Act: 0.0000

Data Index: 1187354 (C4 (Web Text))

Max Activating Token Index: 598

Text #12

Max Range: 1.3620. Min Range: -1.3620

Max Act: 0.1840. Min Act: -0.0000

Data Index: 15074 (C4 (Web Text))

Max Activating Token Index: 695

Text #13

Max Range: 1.3620. Min Range: -1.3620

Max Act: 0.2036. Min Act: -0.0000

Data Index: 663743 (C4 (Web Text))

Max Activating Token Index: 258

Text #14

Max Range: 1.3620. Min Range: -1.3620

Max Act: 0.2168. Min Act: -0.0000

Data Index: 1324217 (C4 (Web Text))

Max Activating Token Index: 924

Text #15

Max Range: 1.3620. Min Range: -1.3620

Max Act: 0.1767. Min Act: 0.0000

Data Index: 278312 (C4 (Web Text))

Max Activating Token Index: 832

Text #16

Max Range: 1.3620. Min Range: -1.3620

Max Act: 0.2050. Min Act: -0.0000

Data Index: 335526 (C4 (Web Text))

Max Activating Token Index: 848

Text #17

Max Range: 1.3620. Min Range: -1.3620

Max Act: 0.1893. Min Act: -0.0000

Data Index: 628247 (C4 (Web Text))

Max Activating Token Index: 42

Text #18

Max Range: 1.3620. Min Range: -1.3620

Max Act: 0.1873. Min Act: -0.0000

Data Index: 272704 (C4 (Web Text))

Max Activating Token Index: 755

Text #19

Max Range: 1.3620. Min Range: -1.3620

Max Act: 0.1949. Min Act: -0.0000

Data Index: 171515 (C4 (Web Text))

Max Activating Token Index: 199