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

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

Neuron 2519 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4017. Min Range: -0.4017

Max Act: 0.4017. Min Act: -0.0000

Data Index: 143233 (C4 (Web Text))

Max Activating Token Index: 84

Text #1

Max Range: 0.4017. Min Range: -0.4017

Max Act: 0.3783. Min Act: -0.0000

Data Index: 783549 (C4 (Web Text))

Max Activating Token Index: 662

Text #2

Max Range: 0.4017. Min Range: -0.4017

Max Act: 0.3703. Min Act: -0.0000

Data Index: 239467 (C4 (Web Text))

Max Activating Token Index: 551

Text #3

Max Range: 0.4017. Min Range: -0.4017

Max Act: 0.3934. Min Act: -0.0000

Data Index: 775604 (C4 (Web Text))

Max Activating Token Index: 575

Text #4

Max Range: 0.4017. Min Range: -0.4017

Max Act: 0.3519. Min Act: -0.0000

Data Index: 478265 (C4 (Web Text))

Max Activating Token Index: 698

Text #5

Max Range: 0.4017. Min Range: -0.4017

Max Act: 0.3740. Min Act: -0.0000

Data Index: 672542 (C4 (Web Text))

Max Activating Token Index: 223

Text #6

Max Range: 0.4017. Min Range: -0.4017

Max Act: 0.3618. Min Act: -0.0000

Data Index: 859184 (C4 (Web Text))

Max Activating Token Index: 799

Text #7

Max Range: 0.4017. Min Range: -0.4017

Max Act: 0.3569. Min Act: -0.0000

Data Index: 916982 (C4 (Web Text))

Max Activating Token Index: 612

Text #8

Max Range: 0.4017. Min Range: -0.4017

Max Act: 0.3601. Min Act: -0.0000

Data Index: 536757 (C4 (Web Text))

Max Activating Token Index: 547

Text #9

Max Range: 0.4017. Min Range: -0.4017

Max Act: 0.3479. Min Act: -0.0000

Data Index: 339136 (C4 (Web Text))

Max Activating Token Index: 791

Text #10

Max Range: 0.4017. Min Range: -0.4017

Max Act: 0.3476. Min Act: -0.0000

Data Index: 938980 (C4 (Web Text))

Max Activating Token Index: 353

Text #11

Max Range: 0.4017. Min Range: -0.4017

Max Act: 0.3454. Min Act: -0.0000

Data Index: 347117 (C4 (Web Text))

Max Activating Token Index: 833

Text #12

Max Range: 0.4017. Min Range: -0.4017

Max Act: 0.3540. Min Act: -0.0000

Data Index: 357935 (C4 (Web Text))

Max Activating Token Index: 54

Text #13

Max Range: 0.4017. Min Range: -0.4017

Max Act: 0.3381. Min Act: -0.0000

Data Index: 1329587 (C4 (Web Text))

Max Activating Token Index: 1003

Text #14

Max Range: 0.4017. Min Range: -0.4017

Max Act: 0.3393. Min Act: -0.0000

Data Index: 1283524 (C4 (Web Text))

Max Activating Token Index: 230

Text #15

Max Range: 0.4017. Min Range: -0.4017

Max Act: 0.3350. Min Act: -0.0000

Data Index: 1192149 (C4 (Web Text))

Max Activating Token Index: 396

Text #16

Max Range: 0.4017. Min Range: -0.4017

Max Act: 0.3512. Min Act: -0.0000

Data Index: 740916 (C4 (Web Text))

Max Activating Token Index: 1007

Text #17

Max Range: 0.4017. Min Range: -0.4017

Max Act: 0.3223. Min Act: -0.0000

Data Index: 1105965 (C4 (Web Text))

Max Activating Token Index: 75

Text #18

Max Range: 0.4017. Min Range: -0.4017

Max Act: 0.3352. Min Act: -0.0000

Data Index: 844094 (C4 (Web Text))

Max Activating Token Index: 791

Text #19

Max Range: 0.4017. Min Range: -0.4017

Max Act: 0.3000. Min Act: -0.0000

Data Index: 886010 (C4 (Web Text))

Max Activating Token Index: 505