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

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

Neuron 3437 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2367. Min Range: -2.2367

Max Act: 2.2367. Min Act: -0.0000

Data Index: 702561 (C4 (Web Text))

Max Activating Token Index: 744

Text #1

Max Range: 2.2367. Min Range: -2.2367

Max Act: 2.1081. Min Act: -0.0000

Data Index: 824534 (C4 (Web Text))

Max Activating Token Index: 94

Text #2

Max Range: 2.2367. Min Range: -2.2367

Max Act: 1.9488. Min Act: -0.0000

Data Index: 297294 (C4 (Web Text))

Max Activating Token Index: 701

Text #3

Max Range: 2.2367. Min Range: -2.2367

Max Act: 1.8449. Min Act: -0.0000

Data Index: 1112345 (C4 (Web Text))

Max Activating Token Index: 224

Text #4

Max Range: 2.2367. Min Range: -2.2367

Max Act: 1.7349. Min Act: -0.0000

Data Index: 848462 (C4 (Web Text))

Max Activating Token Index: 533

Text #5

Max Range: 2.2367. Min Range: -2.2367

Max Act: 1.8253. Min Act: -0.0000

Data Index: 553364 (C4 (Web Text))

Max Activating Token Index: 227

Text #6

Max Range: 2.2367. Min Range: -2.2367

Max Act: 1.7983. Min Act: -0.0000

Data Index: 1344562 (C4 (Web Text))

Max Activating Token Index: 354

Text #7

Max Range: 2.2367. Min Range: -2.2367

Max Act: 1.6721. Min Act: -0.0000

Data Index: 303800 (C4 (Web Text))

Max Activating Token Index: 277

Text #8

Max Range: 2.2367. Min Range: -2.2367

Max Act: 1.6262. Min Act: -0.0000

Data Index: 561265 (C4 (Web Text))

Max Activating Token Index: 150

Text #9

Max Range: 2.2367. Min Range: -2.2367

Max Act: 1.7212. Min Act: -0.0000

Data Index: 1250483 (C4 (Web Text))

Max Activating Token Index: 85

Text #10

Max Range: 2.2367. Min Range: -2.2367

Max Act: 1.8935. Min Act: -0.0000

Data Index: 1020795 (C4 (Web Text))

Max Activating Token Index: 933

Text #11

Max Range: 2.2367. Min Range: -2.2367

Max Act: 1.6186. Min Act: -0.0000

Data Index: 616074 (C4 (Web Text))

Max Activating Token Index: 914

Text #12

Max Range: 2.2367. Min Range: -2.2367

Max Act: 1.6510. Min Act: -0.0000

Data Index: 135923 (C4 (Web Text))

Max Activating Token Index: 803

Text #13

Max Range: 2.2367. Min Range: -2.2367

Max Act: 1.5303. Min Act: -0.0000

Data Index: 673532 (C4 (Web Text))

Max Activating Token Index: 724

Text #14

Max Range: 2.2367. Min Range: -2.2367

Max Act: 1.4931. Min Act: -0.0000

Data Index: 978293 (C4 (Web Text))

Max Activating Token Index: 952

Text #15

Max Range: 2.2367. Min Range: -2.2367

Max Act: 1.4776. Min Act: -0.0000

Data Index: 894194 (C4 (Web Text))

Max Activating Token Index: 416

Text #16

Max Range: 2.2367. Min Range: -2.2367

Max Act: 1.4635. Min Act: -0.0000

Data Index: 1039144 (C4 (Web Text))

Max Activating Token Index: 10

Text #17

Max Range: 2.2367. Min Range: -2.2367

Max Act: 1.3691. Min Act: -0.0000

Data Index: 1252669 (C4 (Web Text))

Max Activating Token Index: 729

Text #18

Max Range: 2.2367. Min Range: -2.2367

Max Act: 1.5213. Min Act: -0.0000

Data Index: 1072632 (C4 (Web Text))

Max Activating Token Index: 184

Text #19

Max Range: 2.2367. Min Range: -2.2367

Max Act: 1.3416. Min Act: -0.0000

Data Index: 1272171 (C4 (Web Text))

Max Activating Token Index: 844