Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4892 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.0117. Min Range: -1.0117

Max Act: 1.0117. Min Act: -0.0002

Data Index: 1183481 (C4 (Web Text))

Max Activating Token Index: 514

Text #1

Max Range: 1.0117. Min Range: -1.0117

Max Act: 0.9438. Min Act: -0.0002

Data Index: 499721 (C4 (Web Text))

Max Activating Token Index: 5

Text #2

Max Range: 1.0117. Min Range: -1.0117

Max Act: 0.8769. Min Act: -0.0002

Data Index: 819743 (C4 (Web Text))

Max Activating Token Index: 626

Text #3

Max Range: 1.0117. Min Range: -1.0117

Max Act: 0.8757. Min Act: -0.0002

Data Index: 949320 (C4 (Web Text))

Max Activating Token Index: 591

Text #4

Max Range: 1.0117. Min Range: -1.0117

Max Act: 0.8744. Min Act: -0.0002

Data Index: 1495381 (Python Code)

Max Activating Token Index: 241

Text #5

Max Range: 1.0117. Min Range: -1.0117

Max Act: 0.8471. Min Act: -0.0002

Data Index: 915246 (C4 (Web Text))

Max Activating Token Index: 737

Text #6

Max Range: 1.0117. Min Range: -1.0117

Max Act: 0.8486. Min Act: -0.0002

Data Index: 1359508 (C4 (Web Text))

Max Activating Token Index: 83

Text #7

Max Range: 1.0117. Min Range: -1.0117

Max Act: 0.7716. Min Act: -0.0002

Data Index: 511107 (C4 (Web Text))

Max Activating Token Index: 717

Text #8

Max Range: 1.0117. Min Range: -1.0117

Max Act: 0.7189. Min Act: -0.0003

Data Index: 596283 (C4 (Web Text))

Max Activating Token Index: 71

Text #9

Max Range: 1.0117. Min Range: -1.0117

Max Act: 0.8735. Min Act: -0.0002

Data Index: 191125 (C4 (Web Text))

Max Activating Token Index: 316

Text #10

Max Range: 1.0117. Min Range: -1.0117

Max Act: 0.7786. Min Act: -0.0002

Data Index: 188673 (C4 (Web Text))

Max Activating Token Index: 870

Text #11

Max Range: 1.0117. Min Range: -1.0117

Max Act: 0.8132. Min Act: -0.0002

Data Index: 47087 (C4 (Web Text))

Max Activating Token Index: 463

Text #12

Max Range: 1.0117. Min Range: -1.0117

Max Act: 0.8178. Min Act: -0.0002

Data Index: 448222 (C4 (Web Text))

Max Activating Token Index: 241

Text #13

Max Range: 1.0117. Min Range: -1.0117

Max Act: 0.7533. Min Act: -0.0002

Data Index: 869757 (C4 (Web Text))

Max Activating Token Index: 694

Text #14

Max Range: 1.0117. Min Range: -1.0117

Max Act: 0.7544. Min Act: -0.0002

Data Index: 645442 (C4 (Web Text))

Max Activating Token Index: 878

Text #15

Max Range: 1.0117. Min Range: -1.0117

Max Act: 0.7522. Min Act: -0.0002

Data Index: 2261 (C4 (Web Text))

Max Activating Token Index: 452

Text #16

Max Range: 1.0117. Min Range: -1.0117

Max Act: 0.7241. Min Act: -0.0002

Data Index: 732859 (C4 (Web Text))

Max Activating Token Index: 598

Text #17

Max Range: 1.0117. Min Range: -1.0117

Max Act: 0.7692. Min Act: -0.0002

Data Index: 1334188 (C4 (Web Text))

Max Activating Token Index: 942

Text #18

Max Range: 1.0117. Min Range: -1.0117

Max Act: 0.7627. Min Act: -0.0002

Data Index: 120103 (C4 (Web Text))

Max Activating Token Index: 513

Text #19

Max Range: 1.0117. Min Range: -1.0117

Max Act: 0.8341. Min Act: -0.0002

Data Index: 752456 (C4 (Web Text))

Max Activating Token Index: 300