Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1048 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0592. Min Act: -0.0001

Data Index: 133 (C4 (Web Text))

Max Activating Token Index: 333

Text #1

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0561. Min Act: -0.0002

Data Index: 104298 (C4 (Web Text))

Max Activating Token Index: 143

Text #2

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0541. Min Act: -0.0002

Data Index: 523657 (C4 (Web Text))

Max Activating Token Index: 27

Text #3

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0532. Min Act: -0.0002

Data Index: 540179 (C4 (Web Text))

Max Activating Token Index: 434

Text #4

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0518. Min Act: -0.0002

Data Index: 758757 (C4 (Web Text))

Max Activating Token Index: 837

Text #5

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0500. Min Act: -0.0002

Data Index: 1022009 (C4 (Web Text))

Max Activating Token Index: 706

Text #6

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0525. Min Act: -0.0002

Data Index: 216657 (C4 (Web Text))

Max Activating Token Index: 135

Text #7

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0485. Min Act: -0.0002

Data Index: 414154 (C4 (Web Text))

Max Activating Token Index: 921

Text #8

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0499. Min Act: -0.0002

Data Index: 345124 (C4 (Web Text))

Max Activating Token Index: 164

Text #9

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0478. Min Act: -0.0001

Data Index: 443750 (C4 (Web Text))

Max Activating Token Index: 288

Text #10

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0492. Min Act: -0.0002

Data Index: 673343 (C4 (Web Text))

Max Activating Token Index: 758

Text #11

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0492. Min Act: -0.0002

Data Index: 58868 (C4 (Web Text))

Max Activating Token Index: 951

Text #12

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0470. Min Act: 0.0001

Data Index: 112118 (C4 (Web Text))

Max Activating Token Index: 27

Text #13

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0472. Min Act: -0.0002

Data Index: 927318 (C4 (Web Text))

Max Activating Token Index: 139

Text #14

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0461. Min Act: -0.0002

Data Index: 1047990 (C4 (Web Text))

Max Activating Token Index: 518

Text #15

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0445. Min Act: -0.0001

Data Index: 70794 (C4 (Web Text))

Max Activating Token Index: 985

Text #16

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0462. Min Act: -0.0002

Data Index: 1312389 (C4 (Web Text))

Max Activating Token Index: 171

Text #17

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0462. Min Act: -0.0002

Data Index: 415465 (C4 (Web Text))

Max Activating Token Index: 133

Text #18

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0474. Min Act: -0.0002

Data Index: 1054759 (C4 (Web Text))

Max Activating Token Index: 850

Text #19

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0461. Min Act: -0.0000

Data Index: 1152570 (C4 (Web Text))

Max Activating Token Index: 566