Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3062 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0944. Min Act: -0.0002

Data Index: 288497 (C4 (Web Text))

Max Activating Token Index: 261

Text #1

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0780. Min Act: -0.0002

Data Index: 152634 (C4 (Web Text))

Max Activating Token Index: 192

Text #2

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0808. Min Act: -0.0002

Data Index: 338092 (C4 (Web Text))

Max Activating Token Index: 107

Text #3

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0804. Min Act: -0.0002

Data Index: 206126 (C4 (Web Text))

Max Activating Token Index: 388

Text #4

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0712. Min Act: -0.0002

Data Index: 938132 (C4 (Web Text))

Max Activating Token Index: 796

Text #5

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0665. Min Act: -0.0002

Data Index: 333094 (C4 (Web Text))

Max Activating Token Index: 809

Text #6

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0660. Min Act: -0.0002

Data Index: 726060 (C4 (Web Text))

Max Activating Token Index: 442

Text #7

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0676. Min Act: -0.0002

Data Index: 873602 (C4 (Web Text))

Max Activating Token Index: 198

Text #8

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0691. Min Act: -0.0002

Data Index: 1172850 (C4 (Web Text))

Max Activating Token Index: 164

Text #9

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0660. Min Act: -0.0002

Data Index: 700523 (C4 (Web Text))

Max Activating Token Index: 328

Text #10

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0679. Min Act: -0.0002

Data Index: 1054331 (C4 (Web Text))

Max Activating Token Index: 621

Text #11

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0654. Min Act: -0.0001

Data Index: 1206398 (C4 (Web Text))

Max Activating Token Index: 43

Text #12

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0653. Min Act: -0.0001

Data Index: 1105774 (C4 (Web Text))

Max Activating Token Index: 791

Text #13

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0646. Min Act: -0.0001

Data Index: 989776 (C4 (Web Text))

Max Activating Token Index: 907

Text #14

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0643. Min Act: -0.0002

Data Index: 822499 (C4 (Web Text))

Max Activating Token Index: 102

Text #15

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0640. Min Act: -0.0002

Data Index: 761703 (C4 (Web Text))

Max Activating Token Index: 751

Text #16

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0659. Min Act: -0.0002

Data Index: 742475 (C4 (Web Text))

Max Activating Token Index: 437

Text #17

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0632. Min Act: -0.0002

Data Index: 1251451 (C4 (Web Text))

Max Activating Token Index: 69

Text #18

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0623. Min Act: -0.0002

Data Index: 1012384 (C4 (Web Text))

Max Activating Token Index: 162

Text #19

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0618. Min Act: -0.0002

Data Index: 608979 (C4 (Web Text))

Max Activating Token Index: 35