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

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

Neuron 1640 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0068. Min Act: -0.0002

Data Index: 1583932 (Python Code)

Max Activating Token Index: 7

Text #1

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0063. Min Act: -0.0003

Data Index: 1100538 (C4 (Web Text))

Max Activating Token Index: 191

Text #2

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0059. Min Act: -0.0003

Data Index: 587463 (C4 (Web Text))

Max Activating Token Index: 90

Text #3

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0058. Min Act: -0.0003

Data Index: 79500 (C4 (Web Text))

Max Activating Token Index: 119

Text #4

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0058. Min Act: -0.0003

Data Index: 183903 (C4 (Web Text))

Max Activating Token Index: 224

Text #5

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0057. Min Act: -0.0003

Data Index: 313126 (C4 (Web Text))

Max Activating Token Index: 604

Text #6

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0053. Min Act: -0.0003

Data Index: 590552 (C4 (Web Text))

Max Activating Token Index: 243

Text #7

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0053. Min Act: -0.0003

Data Index: 95568 (C4 (Web Text))

Max Activating Token Index: 684

Text #8

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0052. Min Act: -0.0002

Data Index: 1629929 (Python Code)

Max Activating Token Index: 279

Text #9

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0051. Min Act: -0.0003

Data Index: 595366 (C4 (Web Text))

Max Activating Token Index: 359

Text #10

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0051. Min Act: -0.0003

Data Index: 277996 (C4 (Web Text))

Max Activating Token Index: 129

Text #11

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0050. Min Act: -0.0002

Data Index: 1417452 (Python Code)

Max Activating Token Index: 352

Text #12

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0050. Min Act: -0.0003

Data Index: 410848 (C4 (Web Text))

Max Activating Token Index: 798

Text #13

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0050. Min Act: -0.0003

Data Index: 366453 (C4 (Web Text))

Max Activating Token Index: 83

Text #14

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0049. Min Act: -0.0003

Data Index: 432121 (C4 (Web Text))

Max Activating Token Index: 104

Text #15

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0049. Min Act: -0.0003

Data Index: 901826 (C4 (Web Text))

Max Activating Token Index: 635

Text #16

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0049. Min Act: -0.0003

Data Index: 460348 (C4 (Web Text))

Max Activating Token Index: 94

Text #17

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0049. Min Act: -0.0003

Data Index: 129914 (C4 (Web Text))

Max Activating Token Index: 694

Text #18

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0048. Min Act: -0.0003

Data Index: 212353 (C4 (Web Text))

Max Activating Token Index: 120

Text #19

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0048. Min Act: -0.0002

Data Index: 1444314 (Python Code)

Max Activating Token Index: 474