Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 5107 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.1347. Min Act: -0.0001

Data Index: 788084 (C4 (Web Text))

Max Activating Token Index: 721

Text #1

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.1382. Min Act: -0.0001

Data Index: 838342 (C4 (Web Text))

Max Activating Token Index: 584

Text #2

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.1293. Min Act: -0.0001

Data Index: 1229847 (C4 (Web Text))

Max Activating Token Index: 674

Text #3

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.1207. Min Act: -0.0001

Data Index: 947807 (C4 (Web Text))

Max Activating Token Index: 277

Text #4

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.1162. Min Act: -0.0001

Data Index: 308642 (C4 (Web Text))

Max Activating Token Index: 182

Text #5

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.1145. Min Act: -0.0001

Data Index: 1079786 (C4 (Web Text))

Max Activating Token Index: 785

Text #6

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.1096. Min Act: -0.0001

Data Index: 1313112 (C4 (Web Text))

Max Activating Token Index: 472

Text #7

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.1133. Min Act: -0.0001

Data Index: 265075 (C4 (Web Text))

Max Activating Token Index: 415

Text #8

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.1147. Min Act: -0.0001

Data Index: 973346 (C4 (Web Text))

Max Activating Token Index: 594

Text #9

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.1138. Min Act: -0.0001

Data Index: 594080 (C4 (Web Text))

Max Activating Token Index: 592

Text #10

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.1089. Min Act: -0.0001

Data Index: 965458 (C4 (Web Text))

Max Activating Token Index: 365

Text #11

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.1092. Min Act: -0.0001

Data Index: 909311 (C4 (Web Text))

Max Activating Token Index: 261

Text #12

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.1076. Min Act: -0.0001

Data Index: 1251619 (C4 (Web Text))

Max Activating Token Index: 971

Text #13

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.1054. Min Act: -0.0001

Data Index: 696016 (C4 (Web Text))

Max Activating Token Index: 891

Text #14

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.0991. Min Act: -0.0001

Data Index: 379277 (C4 (Web Text))

Max Activating Token Index: 258

Text #15

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.1023. Min Act: -0.0001

Data Index: 23883 (C4 (Web Text))

Max Activating Token Index: 200

Text #16

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.1028. Min Act: -0.0001

Data Index: 557143 (C4 (Web Text))

Max Activating Token Index: 982

Text #17

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.1044. Min Act: -0.0001

Data Index: 1358684 (C4 (Web Text))

Max Activating Token Index: 56

Text #18

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.1052. Min Act: -0.0001

Data Index: 1299828 (C4 (Web Text))

Max Activating Token Index: 90

Text #19

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.1042. Min Act: -0.0001

Data Index: 652151 (C4 (Web Text))

Max Activating Token Index: 690