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

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

Neuron 87 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: 0.0601. Min Range: -0.0601

Max Act: 0.0601. Min Act: -0.0002

Data Index: 988860 (C4 (Web Text))

Max Activating Token Index: 317

Text #1

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0579. Min Act: -0.0002

Data Index: 1086183 (C4 (Web Text))

Max Activating Token Index: 985

Text #2

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0563. Min Act: -0.0002

Data Index: 520710 (C4 (Web Text))

Max Activating Token Index: 16

Text #3

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0544. Min Act: -0.0002

Data Index: 241403 (C4 (Web Text))

Max Activating Token Index: 267

Text #4

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0541. Min Act: -0.0002

Data Index: 777270 (C4 (Web Text))

Max Activating Token Index: 138

Text #5

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0546. Min Act: -0.0002

Data Index: 1072401 (C4 (Web Text))

Max Activating Token Index: 498

Text #6

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0553. Min Act: -0.0002

Data Index: 942069 (C4 (Web Text))

Max Activating Token Index: 187

Text #7

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0559. Min Act: -0.0001

Data Index: 534274 (C4 (Web Text))

Max Activating Token Index: 969

Text #8

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0523. Min Act: -0.0002

Data Index: 112729 (C4 (Web Text))

Max Activating Token Index: 103

Text #9

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0563. Min Act: -0.0002

Data Index: 521093 (C4 (Web Text))

Max Activating Token Index: 1014

Text #10

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0513. Min Act: -0.0002

Data Index: 245954 (C4 (Web Text))

Max Activating Token Index: 396

Text #11

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0520. Min Act: -0.0002

Data Index: 172006 (C4 (Web Text))

Max Activating Token Index: 847

Text #12

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0533. Min Act: -0.0002

Data Index: 132404 (C4 (Web Text))

Max Activating Token Index: 739

Text #13

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0543. Min Act: -0.0002

Data Index: 1049553 (C4 (Web Text))

Max Activating Token Index: 990

Text #14

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0484. Min Act: -0.0002

Data Index: 212599 (C4 (Web Text))

Max Activating Token Index: 301

Text #15

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0511. Min Act: -0.0002

Data Index: 905350 (C4 (Web Text))

Max Activating Token Index: 92

Text #16

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0510. Min Act: -0.0002

Data Index: 111235 (C4 (Web Text))

Max Activating Token Index: 156

Text #17

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0516. Min Act: -0.0002

Data Index: 247511 (C4 (Web Text))

Max Activating Token Index: 908

Text #18

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0500. Min Act: -0.0002

Data Index: 686904 (C4 (Web Text))

Max Activating Token Index: 339

Text #19

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0500. Min Act: -0.0002

Data Index: 934619 (C4 (Web Text))

Max Activating Token Index: 213