Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 2005 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0078. Min Range: -0.0078

Max Act: 0.0078. Min Act: -0.0006

Data Index: 172403 (C4 (Web Text))

Max Activating Token Index: 557

Text #1

Max Range: 0.0078. Min Range: -0.0078

Max Act: 0.0076. Min Act: -0.0006

Data Index: 701476 (C4 (Web Text))

Max Activating Token Index: 664

Text #2

Max Range: 0.0078. Min Range: -0.0078

Max Act: 0.0068. Min Act: -0.0006

Data Index: 735334 (C4 (Web Text))

Max Activating Token Index: 611

Text #3

Max Range: 0.0078. Min Range: -0.0078

Max Act: 0.0067. Min Act: -0.0006

Data Index: 750 (C4 (Web Text))

Max Activating Token Index: 139

Text #4

Max Range: 0.0078. Min Range: -0.0078

Max Act: 0.0067. Min Act: -0.0006

Data Index: 783295 (C4 (Web Text))

Max Activating Token Index: 91

Text #5

Max Range: 0.0078. Min Range: -0.0078

Max Act: 0.0067. Min Act: -0.0006

Data Index: 862899 (C4 (Web Text))

Max Activating Token Index: 703

Text #6

Max Range: 0.0078. Min Range: -0.0078

Max Act: 0.0065. Min Act: -0.0006

Data Index: 1246482 (C4 (Web Text))

Max Activating Token Index: 41

Text #7

Max Range: 0.0078. Min Range: -0.0078

Max Act: 0.0065. Min Act: -0.0006

Data Index: 309780 (C4 (Web Text))

Max Activating Token Index: 213

Text #8

Max Range: 0.0078. Min Range: -0.0078

Max Act: 0.0062. Min Act: -0.0006

Data Index: 394435 (C4 (Web Text))

Max Activating Token Index: 155

Text #9

Max Range: 0.0078. Min Range: -0.0078

Max Act: 0.0063. Min Act: -0.0006

Data Index: 747923 (C4 (Web Text))

Max Activating Token Index: 717

Text #10

Max Range: 0.0078. Min Range: -0.0078

Max Act: 0.0063. Min Act: -0.0006

Data Index: 695360 (C4 (Web Text))

Max Activating Token Index: 385

Text #11

Max Range: 0.0078. Min Range: -0.0078

Max Act: 0.0061. Min Act: -0.0006

Data Index: 868297 (C4 (Web Text))

Max Activating Token Index: 53

Text #12

Max Range: 0.0078. Min Range: -0.0078

Max Act: 0.0066. Min Act: -0.0006

Data Index: 588556 (C4 (Web Text))

Max Activating Token Index: 761

Text #13

Max Range: 0.0078. Min Range: -0.0078

Max Act: 0.0062. Min Act: -0.0006

Data Index: 1048712 (C4 (Web Text))

Max Activating Token Index: 930

Text #14

Max Range: 0.0078. Min Range: -0.0078

Max Act: 0.0062. Min Act: -0.0006

Data Index: 906498 (C4 (Web Text))

Max Activating Token Index: 536

Text #15

Max Range: 0.0078. Min Range: -0.0078

Max Act: 0.0065. Min Act: -0.0006

Data Index: 201925 (C4 (Web Text))

Max Activating Token Index: 156

Text #16

Max Range: 0.0078. Min Range: -0.0078

Max Act: 0.0063. Min Act: -0.0006

Data Index: 448487 (C4 (Web Text))

Max Activating Token Index: 488

Text #17

Max Range: 0.0078. Min Range: -0.0078

Max Act: 0.0062. Min Act: -0.0006

Data Index: 199097 (C4 (Web Text))

Max Activating Token Index: 722

Text #18

Max Range: 0.0078. Min Range: -0.0078

Max Act: 0.0061. Min Act: -0.0006

Data Index: 93235 (C4 (Web Text))

Max Activating Token Index: 745

Text #19

Max Range: 0.0078. Min Range: -0.0078

Max Act: 0.0060. Min Act: -0.0006

Data Index: 431026 (C4 (Web Text))

Max Activating Token Index: 477