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

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

Neuron 2943 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9205. Min Range: -0.9205

Max Act: 0.9205. Min Act: -0.0000

Data Index: 315435 (C4 (Web Text))

Max Activating Token Index: 971

Text #1

Max Range: 0.9205. Min Range: -0.9205

Max Act: 0.7619. Min Act: -0.0000

Data Index: 495818 (C4 (Web Text))

Max Activating Token Index: 160

Text #2

Max Range: 0.9205. Min Range: -0.9205

Max Act: 0.8010. Min Act: -0.0000

Data Index: 378077 (C4 (Web Text))

Max Activating Token Index: 418

Text #3

Max Range: 0.9205. Min Range: -0.9205

Max Act: 0.7499. Min Act: -0.0000

Data Index: 660286 (C4 (Web Text))

Max Activating Token Index: 794

Text #4

Max Range: 0.9205. Min Range: -0.9205

Max Act: 0.7204. Min Act: -0.0000

Data Index: 521185 (C4 (Web Text))

Max Activating Token Index: 341

Text #5

Max Range: 0.9205. Min Range: -0.9205

Max Act: 0.7797. Min Act: -0.0000

Data Index: 101818 (C4 (Web Text))

Max Activating Token Index: 368

Text #6

Max Range: 0.9205. Min Range: -0.9205

Max Act: 0.7048. Min Act: -0.0000

Data Index: 1193455 (C4 (Web Text))

Max Activating Token Index: 993

Text #7

Max Range: 0.9205. Min Range: -0.9205

Max Act: 0.6462. Min Act: -0.0000

Data Index: 289776 (C4 (Web Text))

Max Activating Token Index: 988

Text #8

Max Range: 0.9205. Min Range: -0.9205

Max Act: 0.6413. Min Act: -0.0000

Data Index: 483551 (C4 (Web Text))

Max Activating Token Index: 812

Text #9

Max Range: 0.9205. Min Range: -0.9205

Max Act: 0.7294. Min Act: -0.0000

Data Index: 531599 (C4 (Web Text))

Max Activating Token Index: 128

Text #10

Max Range: 0.9205. Min Range: -0.9205

Max Act: 0.6441. Min Act: -0.0000

Data Index: 4781 (C4 (Web Text))

Max Activating Token Index: 688

Text #11

Max Range: 0.9205. Min Range: -0.9205

Max Act: 0.6564. Min Act: -0.0000

Data Index: 369751 (C4 (Web Text))

Max Activating Token Index: 966

Text #12

Max Range: 0.9205. Min Range: -0.9205

Max Act: 0.6514. Min Act: -0.0000

Data Index: 1029682 (C4 (Web Text))

Max Activating Token Index: 226

Text #13

Max Range: 0.9205. Min Range: -0.9205

Max Act: 0.6702. Min Act: -0.0000

Data Index: 99491 (C4 (Web Text))

Max Activating Token Index: 659

Text #14

Max Range: 0.9205. Min Range: -0.9205

Max Act: 0.6751. Min Act: -0.0000

Data Index: 870567 (C4 (Web Text))

Max Activating Token Index: 61

Text #15

Max Range: 0.9205. Min Range: -0.9205

Max Act: 0.6151. Min Act: -0.0000

Data Index: 74137 (C4 (Web Text))

Max Activating Token Index: 999

Text #16

Max Range: 0.9205. Min Range: -0.9205

Max Act: 0.6057. Min Act: -0.0000

Data Index: 627469 (C4 (Web Text))

Max Activating Token Index: 428

Text #17

Max Range: 0.9205. Min Range: -0.9205

Max Act: 0.7124. Min Act: -0.0000

Data Index: 110521 (C4 (Web Text))

Max Activating Token Index: 857

Text #18

Max Range: 0.9205. Min Range: -0.9205

Max Act: 0.6445. Min Act: -0.0000

Data Index: 244797 (C4 (Web Text))

Max Activating Token Index: 108

Text #19

Max Range: 0.9205. Min Range: -0.9205

Max Act: 0.6571. Min Act: -0.0000

Data Index: 1342629 (C4 (Web Text))

Max Activating Token Index: 887