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

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

Neuron 6030 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3332. Min Range: -0.3332

Max Act: 0.3297. Min Act: -0.0000

Data Index: 1326722 (C4 (Web Text))

Max Activating Token Index: 201

Text #1

Max Range: 0.3332. Min Range: -0.3332

Max Act: 0.3332. Min Act: -0.0000

Data Index: 407807 (C4 (Web Text))

Max Activating Token Index: 697

Text #2

Max Range: 0.3332. Min Range: -0.3332

Max Act: 0.3220. Min Act: -0.0000

Data Index: 382032 (C4 (Web Text))

Max Activating Token Index: 270

Text #3

Max Range: 0.3332. Min Range: -0.3332

Max Act: 0.3111. Min Act: -0.0001

Data Index: 764461 (C4 (Web Text))

Max Activating Token Index: 430

Text #4

Max Range: 0.3332. Min Range: -0.3332

Max Act: 0.3031. Min Act: -0.0000

Data Index: 1067252 (C4 (Web Text))

Max Activating Token Index: 302

Text #5

Max Range: 0.3332. Min Range: -0.3332

Max Act: 0.3112. Min Act: -0.0001

Data Index: 1014339 (C4 (Web Text))

Max Activating Token Index: 621

Text #6

Max Range: 0.3332. Min Range: -0.3332

Max Act: 0.2978. Min Act: -0.0000

Data Index: 1182337 (C4 (Web Text))

Max Activating Token Index: 493

Text #7

Max Range: 0.3332. Min Range: -0.3332

Max Act: 0.3046. Min Act: -0.0000

Data Index: 874589 (C4 (Web Text))

Max Activating Token Index: 579

Text #8

Max Range: 0.3332. Min Range: -0.3332

Max Act: 0.3145. Min Act: -0.0000

Data Index: 1142062 (C4 (Web Text))

Max Activating Token Index: 390

Text #9

Max Range: 0.3332. Min Range: -0.3332

Max Act: 0.2633. Min Act: -0.0000

Data Index: 179503 (C4 (Web Text))

Max Activating Token Index: 59

Text #10

Max Range: 0.3332. Min Range: -0.3332

Max Act: 0.2848. Min Act: -0.0000

Data Index: 122871 (C4 (Web Text))

Max Activating Token Index: 730

Text #11

Max Range: 0.3332. Min Range: -0.3332

Max Act: 0.2986. Min Act: -0.0000

Data Index: 962696 (C4 (Web Text))

Max Activating Token Index: 257

Text #12

Max Range: 0.3332. Min Range: -0.3332

Max Act: 0.2859. Min Act: -0.0000

Data Index: 620015 (C4 (Web Text))

Max Activating Token Index: 717

Text #13

Max Range: 0.3332. Min Range: -0.3332

Max Act: 0.2997. Min Act: -0.0000

Data Index: 218018 (C4 (Web Text))

Max Activating Token Index: 730

Text #14

Max Range: 0.3332. Min Range: -0.3332

Max Act: 0.2813. Min Act: -0.0000

Data Index: 1282940 (C4 (Web Text))

Max Activating Token Index: 187

Text #15

Max Range: 0.3332. Min Range: -0.3332

Max Act: 0.2696. Min Act: -0.0000

Data Index: 1230021 (C4 (Web Text))

Max Activating Token Index: 213

Text #16

Max Range: 0.3332. Min Range: -0.3332

Max Act: 0.2684. Min Act: -0.0000

Data Index: 1280432 (C4 (Web Text))

Max Activating Token Index: 156

Text #17

Max Range: 0.3332. Min Range: -0.3332

Max Act: 0.2781. Min Act: -0.0001

Data Index: 969060 (C4 (Web Text))

Max Activating Token Index: 282

Text #18

Max Range: 0.3332. Min Range: -0.3332

Max Act: 0.2650. Min Act: -0.0001

Data Index: 1115668 (C4 (Web Text))

Max Activating Token Index: 87

Text #19

Max Range: 0.3332. Min Range: -0.3332

Max Act: 0.2633. Min Act: -0.0000

Data Index: 1028813 (C4 (Web Text))

Max Activating Token Index: 379