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

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

Neuron 2740 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1169. Min Range: -0.1169

Max Act: 0.1081. Min Act: -0.0001

Data Index: 260110 (C4 (Web Text))

Max Activating Token Index: 801

Text #1

Max Range: 0.1169. Min Range: -0.1169

Max Act: 0.1124. Min Act: -0.0001

Data Index: 1278375 (C4 (Web Text))

Max Activating Token Index: 789

Text #2

Max Range: 0.1169. Min Range: -0.1169

Max Act: 0.1157. Min Act: -0.0001

Data Index: 1321534 (C4 (Web Text))

Max Activating Token Index: 853

Text #3

Max Range: 0.1169. Min Range: -0.1169

Max Act: 0.1032. Min Act: -0.0001

Data Index: 28358 (C4 (Web Text))

Max Activating Token Index: 820

Text #4

Max Range: 0.1169. Min Range: -0.1169

Max Act: 0.1169. Min Act: -0.0001

Data Index: 1243108 (C4 (Web Text))

Max Activating Token Index: 510

Text #5

Max Range: 0.1169. Min Range: -0.1169

Max Act: 0.1063. Min Act: -0.0001

Data Index: 44457 (C4 (Web Text))

Max Activating Token Index: 808

Text #6

Max Range: 0.1169. Min Range: -0.1169

Max Act: 0.1083. Min Act: -0.0001

Data Index: 1188538 (C4 (Web Text))

Max Activating Token Index: 993

Text #7

Max Range: 0.1169. Min Range: -0.1169

Max Act: 0.0980. Min Act: -0.0001

Data Index: 737263 (C4 (Web Text))

Max Activating Token Index: 24

Text #8

Max Range: 0.1169. Min Range: -0.1169

Max Act: 0.1000. Min Act: -0.0001

Data Index: 1198837 (C4 (Web Text))

Max Activating Token Index: 839

Text #9

Max Range: 0.1169. Min Range: -0.1169

Max Act: 0.1013. Min Act: -0.0001

Data Index: 280343 (C4 (Web Text))

Max Activating Token Index: 451

Text #10

Max Range: 0.1169. Min Range: -0.1169

Max Act: 0.1045. Min Act: -0.0001

Data Index: 249237 (C4 (Web Text))

Max Activating Token Index: 193

Text #11

Max Range: 0.1169. Min Range: -0.1169

Max Act: 0.1112. Min Act: -0.0001

Data Index: 1023278 (C4 (Web Text))

Max Activating Token Index: 737

Text #12

Max Range: 0.1169. Min Range: -0.1169

Max Act: 0.1037. Min Act: -0.0001

Data Index: 561320 (C4 (Web Text))

Max Activating Token Index: 150

Text #13

Max Range: 0.1169. Min Range: -0.1169

Max Act: 0.1007. Min Act: -0.0001

Data Index: 1235184 (C4 (Web Text))

Max Activating Token Index: 1016

Text #14

Max Range: 0.1169. Min Range: -0.1169

Max Act: 0.1016. Min Act: -0.0001

Data Index: 675895 (C4 (Web Text))

Max Activating Token Index: 805

Text #15

Max Range: 0.1169. Min Range: -0.1169

Max Act: 0.1092. Min Act: -0.0001

Data Index: 923790 (C4 (Web Text))

Max Activating Token Index: 402

Text #16

Max Range: 0.1169. Min Range: -0.1169

Max Act: 0.0985. Min Act: -0.0001

Data Index: 769420 (C4 (Web Text))

Max Activating Token Index: 503

Text #17

Max Range: 0.1169. Min Range: -0.1169

Max Act: 0.0854. Min Act: -0.0001

Data Index: 266004 (C4 (Web Text))

Max Activating Token Index: 917

Text #18

Max Range: 0.1169. Min Range: -0.1169

Max Act: 0.0938. Min Act: -0.0001

Data Index: 89740 (C4 (Web Text))

Max Activating Token Index: 588

Text #19

Max Range: 0.1169. Min Range: -0.1169

Max Act: 0.0999. Min Act: -0.0001

Data Index: 295196 (C4 (Web Text))

Max Activating Token Index: 231