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

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

Neuron 3303 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3441. Min Range: -2.3441

Max Act: 2.1442. Min Act: -0.0000

Data Index: 489059 (C4 (Web Text))

Max Activating Token Index: 331

Text #1

Max Range: 2.3441. Min Range: -2.3441

Max Act: 2.3441. Min Act: -0.0000

Data Index: 129154 (C4 (Web Text))

Max Activating Token Index: 27

Text #2

Max Range: 2.3441. Min Range: -2.3441

Max Act: 1.7857. Min Act: -0.0000

Data Index: 889591 (C4 (Web Text))

Max Activating Token Index: 170

Text #3

Max Range: 2.3441. Min Range: -2.3441

Max Act: 1.8378. Min Act: -0.0000

Data Index: 968082 (C4 (Web Text))

Max Activating Token Index: 777

Text #4

Max Range: 2.3441. Min Range: -2.3441

Max Act: 1.8274. Min Act: -0.0000

Data Index: 39910 (C4 (Web Text))

Max Activating Token Index: 332

Text #5

Max Range: 2.3441. Min Range: -2.3441

Max Act: 1.5842. Min Act: -0.0000

Data Index: 155293 (C4 (Web Text))

Max Activating Token Index: 990

Text #6

Max Range: 2.3441. Min Range: -2.3441

Max Act: 1.7691. Min Act: -0.0000

Data Index: 68615 (C4 (Web Text))

Max Activating Token Index: 262

Text #7

Max Range: 2.3441. Min Range: -2.3441

Max Act: 1.6854. Min Act: -0.0000

Data Index: 544482 (C4 (Web Text))

Max Activating Token Index: 232

Text #8

Max Range: 2.3441. Min Range: -2.3441

Max Act: 1.5949. Min Act: -0.0000

Data Index: 532405 (C4 (Web Text))

Max Activating Token Index: 552

Text #9

Max Range: 2.3441. Min Range: -2.3441

Max Act: 1.5908. Min Act: -0.0000

Data Index: 10175 (C4 (Web Text))

Max Activating Token Index: 655

Text #10

Max Range: 2.3441. Min Range: -2.3441

Max Act: 1.4886. Min Act: -0.0000

Data Index: 333901 (C4 (Web Text))

Max Activating Token Index: 524

Text #11

Max Range: 2.3441. Min Range: -2.3441

Max Act: 1.5880. Min Act: -0.0000

Data Index: 557462 (C4 (Web Text))

Max Activating Token Index: 987

Text #12

Max Range: 2.3441. Min Range: -2.3441

Max Act: 1.6601. Min Act: -0.0000

Data Index: 759623 (C4 (Web Text))

Max Activating Token Index: 785

Text #13

Max Range: 2.3441. Min Range: -2.3441

Max Act: 1.5309. Min Act: -0.0000

Data Index: 73341 (C4 (Web Text))

Max Activating Token Index: 147

Text #14

Max Range: 2.3441. Min Range: -2.3441

Max Act: 1.6121. Min Act: -0.0000

Data Index: 808515 (C4 (Web Text))

Max Activating Token Index: 500

Text #15

Max Range: 2.3441. Min Range: -2.3441

Max Act: 1.6129. Min Act: -0.0000

Data Index: 574611 (C4 (Web Text))

Max Activating Token Index: 469

Text #16

Max Range: 2.3441. Min Range: -2.3441

Max Act: 1.5219. Min Act: -0.0000

Data Index: 1006002 (C4 (Web Text))

Max Activating Token Index: 349

Text #17

Max Range: 2.3441. Min Range: -2.3441

Max Act: 1.5359. Min Act: -0.0000

Data Index: 460795 (C4 (Web Text))

Max Activating Token Index: 697

Text #18

Max Range: 2.3441. Min Range: -2.3441

Max Act: 1.5040. Min Act: -0.0000

Data Index: 1146630 (C4 (Web Text))

Max Activating Token Index: 724

Text #19

Max Range: 2.3441. Min Range: -2.3441

Max Act: 1.4936. Min Act: -0.0000

Data Index: 473897 (C4 (Web Text))

Max Activating Token Index: 820