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

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

Neuron 4919 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: 0.1322. Min Range: -0.1322

Max Act: 0.1309. Min Act: -0.0001

Data Index: 233728 (C4 (Web Text))

Max Activating Token Index: 838

Text #1

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.1277. Min Act: -0.0001

Data Index: 181744 (C4 (Web Text))

Max Activating Token Index: 904

Text #2

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.1209. Min Act: -0.0001

Data Index: 764004 (C4 (Web Text))

Max Activating Token Index: 970

Text #3

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.1240. Min Act: -0.0001

Data Index: 598735 (C4 (Web Text))

Max Activating Token Index: 985

Text #4

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.1169. Min Act: -0.0001

Data Index: 998386 (C4 (Web Text))

Max Activating Token Index: 22

Text #5

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.1231. Min Act: -0.0001

Data Index: 830921 (C4 (Web Text))

Max Activating Token Index: 306

Text #6

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.1322. Min Act: -0.0001

Data Index: 201684 (C4 (Web Text))

Max Activating Token Index: 688

Text #7

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.1171. Min Act: -0.0001

Data Index: 1216765 (C4 (Web Text))

Max Activating Token Index: 775

Text #8

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.1103. Min Act: -0.0001

Data Index: 1230830 (C4 (Web Text))

Max Activating Token Index: 91

Text #9

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.1070. Min Act: -0.0001

Data Index: 846249 (C4 (Web Text))

Max Activating Token Index: 236

Text #10

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.1106. Min Act: -0.0001

Data Index: 705214 (C4 (Web Text))

Max Activating Token Index: 44

Text #11

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.1102. Min Act: -0.0001

Data Index: 879834 (C4 (Web Text))

Max Activating Token Index: 284

Text #12

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.1166. Min Act: -0.0001

Data Index: 747506 (C4 (Web Text))

Max Activating Token Index: 16

Text #13

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.1112. Min Act: -0.0001

Data Index: 1138740 (C4 (Web Text))

Max Activating Token Index: 61

Text #14

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.1134. Min Act: -0.0001

Data Index: 56539 (C4 (Web Text))

Max Activating Token Index: 236

Text #15

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.1010. Min Act: -0.0001

Data Index: 799425 (C4 (Web Text))

Max Activating Token Index: 78

Text #16

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.1053. Min Act: -0.0001

Data Index: 623267 (C4 (Web Text))

Max Activating Token Index: 6

Text #17

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.1165. Min Act: -0.0001

Data Index: 412946 (C4 (Web Text))

Max Activating Token Index: 430

Text #18

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.1018. Min Act: -0.0001

Data Index: 484051 (C4 (Web Text))

Max Activating Token Index: 691

Text #19

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.0990. Min Act: -0.0001

Data Index: 684302 (C4 (Web Text))

Max Activating Token Index: 15