Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1997 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2166. Min Range: -0.2166

Max Act: 0.1906. Min Act: -0.0001

Data Index: 1197750 (C4 (Web Text))

Max Activating Token Index: 867

Text #1

Max Range: 0.2166. Min Range: -0.2166

Max Act: 0.2166. Min Act: -0.0002

Data Index: 363469 (C4 (Web Text))

Max Activating Token Index: 660

Text #2

Max Range: 0.2166. Min Range: -0.2166

Max Act: 0.2136. Min Act: -0.0002

Data Index: 110792 (C4 (Web Text))

Max Activating Token Index: 363

Text #3

Max Range: 0.2166. Min Range: -0.2166

Max Act: 0.1976. Min Act: -0.0002

Data Index: 1234834 (C4 (Web Text))

Max Activating Token Index: 383

Text #4

Max Range: 0.2166. Min Range: -0.2166

Max Act: 0.2115. Min Act: -0.0002

Data Index: 562009 (C4 (Web Text))

Max Activating Token Index: 856

Text #5

Max Range: 0.2166. Min Range: -0.2166

Max Act: 0.2141. Min Act: -0.0002

Data Index: 995170 (C4 (Web Text))

Max Activating Token Index: 145

Text #6

Max Range: 0.2166. Min Range: -0.2166

Max Act: 0.2047. Min Act: -0.0001

Data Index: 801110 (C4 (Web Text))

Max Activating Token Index: 231

Text #7

Max Range: 0.2166. Min Range: -0.2166

Max Act: 0.1956. Min Act: -0.0001

Data Index: 537611 (C4 (Web Text))

Max Activating Token Index: 137

Text #8

Max Range: 0.2166. Min Range: -0.2166

Max Act: 0.2026. Min Act: -0.0002

Data Index: 978703 (C4 (Web Text))

Max Activating Token Index: 674

Text #9

Max Range: 0.2166. Min Range: -0.2166

Max Act: 0.1753. Min Act: -0.0001

Data Index: 617622 (C4 (Web Text))

Max Activating Token Index: 790

Text #10

Max Range: 0.2166. Min Range: -0.2166

Max Act: 0.2082. Min Act: -0.0002

Data Index: 1137444 (C4 (Web Text))

Max Activating Token Index: 199

Text #11

Max Range: 0.2166. Min Range: -0.2166

Max Act: 0.1890. Min Act: -0.0001

Data Index: 1300296 (C4 (Web Text))

Max Activating Token Index: 149

Text #12

Max Range: 0.2166. Min Range: -0.2166

Max Act: 0.2075. Min Act: -0.0002

Data Index: 1190169 (C4 (Web Text))

Max Activating Token Index: 1002

Text #13

Max Range: 0.2166. Min Range: -0.2166

Max Act: 0.2069. Min Act: -0.0002

Data Index: 984712 (C4 (Web Text))

Max Activating Token Index: 612

Text #14

Max Range: 0.2166. Min Range: -0.2166

Max Act: 0.2002. Min Act: -0.0002

Data Index: 400862 (C4 (Web Text))

Max Activating Token Index: 902

Text #15

Max Range: 0.2166. Min Range: -0.2166

Max Act: 0.1740. Min Act: -0.0002

Data Index: 685889 (C4 (Web Text))

Max Activating Token Index: 910

Text #16

Max Range: 0.2166. Min Range: -0.2166

Max Act: 0.1995. Min Act: -0.0001

Data Index: 999645 (C4 (Web Text))

Max Activating Token Index: 582

Text #17

Max Range: 0.2166. Min Range: -0.2166

Max Act: 0.1992. Min Act: -0.0002

Data Index: 62556 (C4 (Web Text))

Max Activating Token Index: 598

Text #18

Max Range: 0.2166. Min Range: -0.2166

Max Act: 0.2074. Min Act: -0.0002

Data Index: 1228620 (C4 (Web Text))

Max Activating Token Index: 424

Text #19

Max Range: 0.2166. Min Range: -0.2166

Max Act: 0.2148. Min Act: -0.0001

Data Index: 454714 (C4 (Web Text))

Max Activating Token Index: 206