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

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

Neuron 1665 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: 4.2047. Min Range: -4.2047

Max Act: 4.2047. Min Act: -0.0000

Data Index: 1324808 (C4 (Web Text))

Max Activating Token Index: 187

Text #1

Max Range: 4.2047. Min Range: -4.2047

Max Act: 3.4757. Min Act: -0.0000

Data Index: 1119423 (C4 (Web Text))

Max Activating Token Index: 660

Text #2

Max Range: 4.2047. Min Range: -4.2047

Max Act: 3.6325. Min Act: -0.0000

Data Index: 454010 (C4 (Web Text))

Max Activating Token Index: 123

Text #3

Max Range: 4.2047. Min Range: -4.2047

Max Act: 2.9599. Min Act: -0.0000

Data Index: 1270770 (C4 (Web Text))

Max Activating Token Index: 904

Text #4

Max Range: 4.2047. Min Range: -4.2047

Max Act: 2.9334. Min Act: -0.0000

Data Index: 18024 (C4 (Web Text))

Max Activating Token Index: 664

Text #5

Max Range: 4.2047. Min Range: -4.2047

Max Act: 2.9345. Min Act: -0.0000

Data Index: 1074389 (C4 (Web Text))

Max Activating Token Index: 711

Text #6

Max Range: 4.2047. Min Range: -4.2047

Max Act: 2.8386. Min Act: -0.0000

Data Index: 1031397 (C4 (Web Text))

Max Activating Token Index: 785

Text #7

Max Range: 4.2047. Min Range: -4.2047

Max Act: 2.8050. Min Act: -0.0000

Data Index: 174304 (C4 (Web Text))

Max Activating Token Index: 229

Text #8

Max Range: 4.2047. Min Range: -4.2047

Max Act: 2.8095. Min Act: -0.0000

Data Index: 349987 (C4 (Web Text))

Max Activating Token Index: 760

Text #9

Max Range: 4.2047. Min Range: -4.2047

Max Act: 2.9222. Min Act: -0.0000

Data Index: 1049004 (C4 (Web Text))

Max Activating Token Index: 996

Text #10

Max Range: 4.2047. Min Range: -4.2047

Max Act: 2.7416. Min Act: -0.0000

Data Index: 1175178 (C4 (Web Text))

Max Activating Token Index: 725

Text #11

Max Range: 4.2047. Min Range: -4.2047

Max Act: 2.8165. Min Act: -0.0000

Data Index: 10454 (C4 (Web Text))

Max Activating Token Index: 336

Text #12

Max Range: 4.2047. Min Range: -4.2047

Max Act: 2.7988. Min Act: -0.0000

Data Index: 532045 (C4 (Web Text))

Max Activating Token Index: 600

Text #13

Max Range: 4.2047. Min Range: -4.2047

Max Act: 2.8033. Min Act: -0.0000

Data Index: 362304 (C4 (Web Text))

Max Activating Token Index: 441

Text #14

Max Range: 4.2047. Min Range: -4.2047

Max Act: 2.7938. Min Act: -0.0000

Data Index: 964197 (C4 (Web Text))

Max Activating Token Index: 506

Text #15

Max Range: 4.2047. Min Range: -4.2047

Max Act: 2.7598. Min Act: -0.0000

Data Index: 147316 (C4 (Web Text))

Max Activating Token Index: 954

Text #16

Max Range: 4.2047. Min Range: -4.2047

Max Act: 2.7517. Min Act: -0.0000

Data Index: 501402 (C4 (Web Text))

Max Activating Token Index: 709

Text #17

Max Range: 4.2047. Min Range: -4.2047

Max Act: 2.7122. Min Act: -0.0000

Data Index: 241659 (C4 (Web Text))

Max Activating Token Index: 124

Text #18

Max Range: 4.2047. Min Range: -4.2047

Max Act: 2.7021. Min Act: -0.0000

Data Index: 589839 (C4 (Web Text))

Max Activating Token Index: 67

Text #19

Max Range: 4.2047. Min Range: -4.2047

Max Act: 2.5691. Min Act: -0.0000

Data Index: 1078959 (C4 (Web Text))

Max Activating Token Index: 366