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

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

Neuron 5399 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: 0.3224. Min Range: -0.3224

Max Act: 0.3224. Min Act: -0.0001

Data Index: 649299 (C4 (Web Text))

Max Activating Token Index: 1005

Text #1

Max Range: 0.3224. Min Range: -0.3224

Max Act: 0.2841. Min Act: -0.0001

Data Index: 703467 (C4 (Web Text))

Max Activating Token Index: 144

Text #2

Max Range: 0.3224. Min Range: -0.3224

Max Act: 0.2881. Min Act: -0.0001

Data Index: 990622 (C4 (Web Text))

Max Activating Token Index: 750

Text #3

Max Range: 0.3224. Min Range: -0.3224

Max Act: 0.2855. Min Act: -0.0001

Data Index: 1275565 (C4 (Web Text))

Max Activating Token Index: 370

Text #4

Max Range: 0.3224. Min Range: -0.3224

Max Act: 0.2581. Min Act: -0.0001

Data Index: 1001187 (C4 (Web Text))

Max Activating Token Index: 844

Text #5

Max Range: 0.3224. Min Range: -0.3224

Max Act: 0.2211. Min Act: -0.0000

Data Index: 678298 (C4 (Web Text))

Max Activating Token Index: 233

Text #6

Max Range: 0.3224. Min Range: -0.3224

Max Act: 0.2156. Min Act: -0.0001

Data Index: 72582 (C4 (Web Text))

Max Activating Token Index: 915

Text #7

Max Range: 0.3224. Min Range: -0.3224

Max Act: 0.2123. Min Act: -0.0000

Data Index: 1084556 (C4 (Web Text))

Max Activating Token Index: 424

Text #8

Max Range: 0.3224. Min Range: -0.3224

Max Act: 0.2169. Min Act: -0.0001

Data Index: 144530 (C4 (Web Text))

Max Activating Token Index: 983

Text #9

Max Range: 0.3224. Min Range: -0.3224

Max Act: 0.2135. Min Act: -0.0001

Data Index: 857238 (C4 (Web Text))

Max Activating Token Index: 267

Text #10

Max Range: 0.3224. Min Range: -0.3224

Max Act: 0.2021. Min Act: -0.0000

Data Index: 1143270 (C4 (Web Text))

Max Activating Token Index: 388

Text #11

Max Range: 0.3224. Min Range: -0.3224

Max Act: 0.1876. Min Act: -0.0001

Data Index: 457245 (C4 (Web Text))

Max Activating Token Index: 653

Text #12

Max Range: 0.3224. Min Range: -0.3224

Max Act: 0.1884. Min Act: -0.0001

Data Index: 825276 (C4 (Web Text))

Max Activating Token Index: 351

Text #13

Max Range: 0.3224. Min Range: -0.3224

Max Act: 0.1957. Min Act: -0.0001

Data Index: 282325 (C4 (Web Text))

Max Activating Token Index: 875

Text #14

Max Range: 0.3224. Min Range: -0.3224

Max Act: 0.1980. Min Act: -0.0001

Data Index: 833442 (C4 (Web Text))

Max Activating Token Index: 700

Text #15

Max Range: 0.3224. Min Range: -0.3224

Max Act: 0.2011. Min Act: -0.0001

Data Index: 1201909 (C4 (Web Text))

Max Activating Token Index: 684

Text #16

Max Range: 0.3224. Min Range: -0.3224

Max Act: 0.2008. Min Act: -0.0001

Data Index: 1092713 (C4 (Web Text))

Max Activating Token Index: 13

Text #17

Max Range: 0.3224. Min Range: -0.3224

Max Act: 0.1926. Min Act: -0.0001

Data Index: 306733 (C4 (Web Text))

Max Activating Token Index: 408

Text #18

Max Range: 0.3224. Min Range: -0.3224

Max Act: 0.1941. Min Act: -0.0000

Data Index: 1041220 (C4 (Web Text))

Max Activating Token Index: 315

Text #19

Max Range: 0.3224. Min Range: -0.3224

Max Act: 0.1934. Min Act: -0.0001

Data Index: 422831 (C4 (Web Text))

Max Activating Token Index: 404