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

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

Neuron 2923 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: 0.6052. Min Range: -0.6052

Max Act: 0.6052. Min Act: -0.0002

Data Index: 714032 (C4 (Web Text))

Max Activating Token Index: 809

Text #1

Max Range: 0.6052. Min Range: -0.6052

Max Act: 0.5815. Min Act: -0.0002

Data Index: 1337574 (C4 (Web Text))

Max Activating Token Index: 922

Text #2

Max Range: 0.6052. Min Range: -0.6052

Max Act: 0.5589. Min Act: -0.0002

Data Index: 80890 (C4 (Web Text))

Max Activating Token Index: 794

Text #3

Max Range: 0.6052. Min Range: -0.6052

Max Act: 0.5388. Min Act: -0.0001

Data Index: 250153 (C4 (Web Text))

Max Activating Token Index: 321

Text #4

Max Range: 0.6052. Min Range: -0.6052

Max Act: 0.5435. Min Act: -0.0001

Data Index: 1255828 (C4 (Web Text))

Max Activating Token Index: 317

Text #5

Max Range: 0.6052. Min Range: -0.6052

Max Act: 0.5377. Min Act: -0.0002

Data Index: 651109 (C4 (Web Text))

Max Activating Token Index: 557

Text #6

Max Range: 0.6052. Min Range: -0.6052

Max Act: 0.5167. Min Act: -0.0002

Data Index: 9869 (C4 (Web Text))

Max Activating Token Index: 1013

Text #7

Max Range: 0.6052. Min Range: -0.6052

Max Act: 0.5407. Min Act: -0.0001

Data Index: 1079198 (C4 (Web Text))

Max Activating Token Index: 146

Text #8

Max Range: 0.6052. Min Range: -0.6052

Max Act: 0.5206. Min Act: -0.0002

Data Index: 741551 (C4 (Web Text))

Max Activating Token Index: 247

Text #9

Max Range: 0.6052. Min Range: -0.6052

Max Act: 0.5187. Min Act: -0.0002

Data Index: 223937 (C4 (Web Text))

Max Activating Token Index: 914

Text #10

Max Range: 0.6052. Min Range: -0.6052

Max Act: 0.5075. Min Act: -0.0002

Data Index: 1057613 (C4 (Web Text))

Max Activating Token Index: 952

Text #11

Max Range: 0.6052. Min Range: -0.6052

Max Act: 0.5099. Min Act: -0.0002

Data Index: 77018 (C4 (Web Text))

Max Activating Token Index: 809

Text #12

Max Range: 0.6052. Min Range: -0.6052

Max Act: 0.5230. Min Act: -0.0002

Data Index: 1257281 (C4 (Web Text))

Max Activating Token Index: 844

Text #13

Max Range: 0.6052. Min Range: -0.6052

Max Act: 0.5087. Min Act: -0.0002

Data Index: 248584 (C4 (Web Text))

Max Activating Token Index: 241

Text #14

Max Range: 0.6052. Min Range: -0.6052

Max Act: 0.4958. Min Act: -0.0001

Data Index: 892350 (C4 (Web Text))

Max Activating Token Index: 899

Text #15

Max Range: 0.6052. Min Range: -0.6052

Max Act: 0.4942. Min Act: -0.0001

Data Index: 390842 (C4 (Web Text))

Max Activating Token Index: 409

Text #16

Max Range: 0.6052. Min Range: -0.6052

Max Act: 0.5039. Min Act: -0.0002

Data Index: 1029081 (C4 (Web Text))

Max Activating Token Index: 839

Text #17

Max Range: 0.6052. Min Range: -0.6052

Max Act: 0.5243. Min Act: -0.0001

Data Index: 564788 (C4 (Web Text))

Max Activating Token Index: 679

Text #18

Max Range: 0.6052. Min Range: -0.6052

Max Act: 0.4822. Min Act: -0.0002

Data Index: 1225481 (C4 (Web Text))

Max Activating Token Index: 576

Text #19

Max Range: 0.6052. Min Range: -0.6052

Max Act: 0.4994. Min Act: -0.0001

Data Index: 870699 (C4 (Web Text))

Max Activating Token Index: 386