Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 943 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0049. Min Range: -0.0049

Max Act: 0.0049. Min Act: -0.0004

Data Index: 946405 (C4 (Web Text))

Max Activating Token Index: 513

Text #1

Max Range: 0.0049. Min Range: -0.0049

Max Act: 0.0048. Min Act: -0.0003

Data Index: 598182 (C4 (Web Text))

Max Activating Token Index: 954

Text #2

Max Range: 0.0049. Min Range: -0.0049

Max Act: 0.0046. Min Act: -0.0004

Data Index: 474799 (C4 (Web Text))

Max Activating Token Index: 544

Text #3

Max Range: 0.0049. Min Range: -0.0049

Max Act: 0.0045. Min Act: -0.0003

Data Index: 1624079 (Python Code)

Max Activating Token Index: 189

Text #4

Max Range: 0.0049. Min Range: -0.0049

Max Act: 0.0045. Min Act: -0.0003

Data Index: 612525 (C4 (Web Text))

Max Activating Token Index: 89

Text #5

Max Range: 0.0049. Min Range: -0.0049

Max Act: 0.0045. Min Act: -0.0004

Data Index: 1048504 (C4 (Web Text))

Max Activating Token Index: 973

Text #6

Max Range: 0.0049. Min Range: -0.0049

Max Act: 0.0044. Min Act: -0.0003

Data Index: 880865 (C4 (Web Text))

Max Activating Token Index: 164

Text #7

Max Range: 0.0049. Min Range: -0.0049

Max Act: 0.0044. Min Act: -0.0003

Data Index: 1444100 (Python Code)

Max Activating Token Index: 300

Text #8

Max Range: 0.0049. Min Range: -0.0049

Max Act: 0.0044. Min Act: -0.0003

Data Index: 106663 (C4 (Web Text))

Max Activating Token Index: 56

Text #9

Max Range: 0.0049. Min Range: -0.0049

Max Act: 0.0044. Min Act: -0.0003

Data Index: 1255643 (C4 (Web Text))

Max Activating Token Index: 743

Text #10

Max Range: 0.0049. Min Range: -0.0049

Max Act: 0.0044. Min Act: -0.0003

Data Index: 1559745 (Python Code)

Max Activating Token Index: 373

Text #11

Max Range: 0.0049. Min Range: -0.0049

Max Act: 0.0044. Min Act: -0.0003

Data Index: 448580 (C4 (Web Text))

Max Activating Token Index: 89

Text #12

Max Range: 0.0049. Min Range: -0.0049

Max Act: 0.0044. Min Act: -0.0003

Data Index: 1611971 (Python Code)

Max Activating Token Index: 359

Text #13

Max Range: 0.0049. Min Range: -0.0049

Max Act: 0.0044. Min Act: -0.0003

Data Index: 1187502 (C4 (Web Text))

Max Activating Token Index: 296

Text #14

Max Range: 0.0049. Min Range: -0.0049

Max Act: 0.0044. Min Act: -0.0003

Data Index: 991738 (C4 (Web Text))

Max Activating Token Index: 296

Text #15

Max Range: 0.0049. Min Range: -0.0049

Max Act: 0.0043. Min Act: -0.0003

Data Index: 1134418 (C4 (Web Text))

Max Activating Token Index: 739

Text #16

Max Range: 0.0049. Min Range: -0.0049

Max Act: 0.0043. Min Act: -0.0003

Data Index: 382253 (C4 (Web Text))

Max Activating Token Index: 222

Text #17

Max Range: 0.0049. Min Range: -0.0049

Max Act: 0.0043. Min Act: -0.0003

Data Index: 1501639 (Python Code)

Max Activating Token Index: 389

Text #18

Max Range: 0.0049. Min Range: -0.0049

Max Act: 0.0043. Min Act: -0.0004

Data Index: 744224 (C4 (Web Text))

Max Activating Token Index: 742

Text #19

Max Range: 0.0049. Min Range: -0.0049

Max Act: 0.0043. Min Act: -0.0004

Data Index: 658470 (C4 (Web Text))

Max Activating Token Index: 18