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

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

Neuron 3331 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3088. Min Range: -0.3088

Max Act: 0.3088. Min Act: -0.0000

Data Index: 514472 (C4 (Web Text))

Max Activating Token Index: 788

Text #1

Max Range: 0.3088. Min Range: -0.3088

Max Act: 0.3010. Min Act: -0.0000

Data Index: 365683 (C4 (Web Text))

Max Activating Token Index: 421

Text #2

Max Range: 0.3088. Min Range: -0.3088

Max Act: 0.2664. Min Act: -0.0000

Data Index: 570954 (C4 (Web Text))

Max Activating Token Index: 137

Text #3

Max Range: 0.3088. Min Range: -0.3088

Max Act: 0.2700. Min Act: -0.0000

Data Index: 262156 (C4 (Web Text))

Max Activating Token Index: 727

Text #4

Max Range: 0.3088. Min Range: -0.3088

Max Act: 0.2648. Min Act: -0.0000

Data Index: 664496 (C4 (Web Text))

Max Activating Token Index: 15

Text #5

Max Range: 0.3088. Min Range: -0.3088

Max Act: 0.2627. Min Act: -0.0000

Data Index: 1043302 (C4 (Web Text))

Max Activating Token Index: 178

Text #6

Max Range: 0.3088. Min Range: -0.3088

Max Act: 0.2322. Min Act: -0.0000

Data Index: 1333628 (C4 (Web Text))

Max Activating Token Index: 804

Text #7

Max Range: 0.3088. Min Range: -0.3088

Max Act: 0.2317. Min Act: -0.0000

Data Index: 538824 (C4 (Web Text))

Max Activating Token Index: 192

Text #8

Max Range: 0.3088. Min Range: -0.3088

Max Act: 0.2391. Min Act: -0.0000

Data Index: 494857 (C4 (Web Text))

Max Activating Token Index: 333

Text #9

Max Range: 0.3088. Min Range: -0.3088

Max Act: 0.2242. Min Act: -0.0000

Data Index: 170758 (C4 (Web Text))

Max Activating Token Index: 833

Text #10

Max Range: 0.3088. Min Range: -0.3088

Max Act: 0.2328. Min Act: -0.0001

Data Index: 34101 (C4 (Web Text))

Max Activating Token Index: 154

Text #11

Max Range: 0.3088. Min Range: -0.3088

Max Act: 0.2303. Min Act: -0.0000

Data Index: 595978 (C4 (Web Text))

Max Activating Token Index: 671

Text #12

Max Range: 0.3088. Min Range: -0.3088

Max Act: 0.2225. Min Act: -0.0000

Data Index: 1333564 (C4 (Web Text))

Max Activating Token Index: 205

Text #13

Max Range: 0.3088. Min Range: -0.3088

Max Act: 0.2213. Min Act: -0.0000

Data Index: 71938 (C4 (Web Text))

Max Activating Token Index: 460

Text #14

Max Range: 0.3088. Min Range: -0.3088

Max Act: 0.2202. Min Act: -0.0000

Data Index: 645856 (C4 (Web Text))

Max Activating Token Index: 525

Text #15

Max Range: 0.3088. Min Range: -0.3088

Max Act: 0.1928. Min Act: -0.0000

Data Index: 707633 (C4 (Web Text))

Max Activating Token Index: 882

Text #16

Max Range: 0.3088. Min Range: -0.3088

Max Act: 0.2139. Min Act: -0.0000

Data Index: 144454 (C4 (Web Text))

Max Activating Token Index: 1002

Text #17

Max Range: 0.3088. Min Range: -0.3088

Max Act: 0.2120. Min Act: -0.0000

Data Index: 940998 (C4 (Web Text))

Max Activating Token Index: 819

Text #18

Max Range: 0.3088. Min Range: -0.3088

Max Act: 0.1951. Min Act: -0.0000

Data Index: 392743 (C4 (Web Text))

Max Activating Token Index: 988

Text #19

Max Range: 0.3088. Min Range: -0.3088

Max Act: 0.2004. Min Act: -0.0000

Data Index: 477971 (C4 (Web Text))

Max Activating Token Index: 130