Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2966 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.8197. Min Range: -0.8197

Max Act: 0.8197. Min Act: -0.0000

Data Index: 726797 (C4 (Web Text))

Max Activating Token Index: 617

Text #1

Max Range: 0.8197. Min Range: -0.8197

Max Act: 0.7558. Min Act: -0.0001

Data Index: 1352020 (C4 (Web Text))

Max Activating Token Index: 552

Text #2

Max Range: 0.8197. Min Range: -0.8197

Max Act: 0.7054. Min Act: -0.0000

Data Index: 736223 (C4 (Web Text))

Max Activating Token Index: 732

Text #3

Max Range: 0.8197. Min Range: -0.8197

Max Act: 0.7266. Min Act: -0.0000

Data Index: 928698 (C4 (Web Text))

Max Activating Token Index: 313

Text #4

Max Range: 0.8197. Min Range: -0.8197

Max Act: 0.6756. Min Act: -0.0000

Data Index: 516305 (C4 (Web Text))

Max Activating Token Index: 582

Text #5

Max Range: 0.8197. Min Range: -0.8197

Max Act: 0.6909. Min Act: -0.0000

Data Index: 136722 (C4 (Web Text))

Max Activating Token Index: 255

Text #6

Max Range: 0.8197. Min Range: -0.8197

Max Act: 0.6628. Min Act: -0.0001

Data Index: 3312 (C4 (Web Text))

Max Activating Token Index: 285

Text #7

Max Range: 0.8197. Min Range: -0.8197

Max Act: 0.6513. Min Act: -0.0001

Data Index: 330277 (C4 (Web Text))

Max Activating Token Index: 582

Text #8

Max Range: 0.8197. Min Range: -0.8197

Max Act: 0.6004. Min Act: -0.0000

Data Index: 945498 (C4 (Web Text))

Max Activating Token Index: 895

Text #9

Max Range: 0.8197. Min Range: -0.8197

Max Act: 0.6332. Min Act: -0.0000

Data Index: 732103 (C4 (Web Text))

Max Activating Token Index: 500

Text #10

Max Range: 0.8197. Min Range: -0.8197

Max Act: 0.6317. Min Act: -0.0000

Data Index: 393038 (C4 (Web Text))

Max Activating Token Index: 399

Text #11

Max Range: 0.8197. Min Range: -0.8197

Max Act: 0.5520. Min Act: -0.0000

Data Index: 15670 (C4 (Web Text))

Max Activating Token Index: 246

Text #12

Max Range: 0.8197. Min Range: -0.8197

Max Act: 0.5873. Min Act: -0.0001

Data Index: 1097888 (C4 (Web Text))

Max Activating Token Index: 174

Text #13

Max Range: 0.8197. Min Range: -0.8197

Max Act: 0.5861. Min Act: -0.0000

Data Index: 1098579 (C4 (Web Text))

Max Activating Token Index: 643

Text #14

Max Range: 0.8197. Min Range: -0.8197

Max Act: 0.5789. Min Act: -0.0001

Data Index: 1105665 (C4 (Web Text))

Max Activating Token Index: 493

Text #15

Max Range: 0.8197. Min Range: -0.8197

Max Act: 0.5925. Min Act: -0.0000

Data Index: 578492 (C4 (Web Text))

Max Activating Token Index: 43

Text #16

Max Range: 0.8197. Min Range: -0.8197

Max Act: 0.5540. Min Act: -0.0001

Data Index: 469494 (C4 (Web Text))

Max Activating Token Index: 81

Text #17

Max Range: 0.8197. Min Range: -0.8197

Max Act: 0.5847. Min Act: -0.0000

Data Index: 1345898 (C4 (Web Text))

Max Activating Token Index: 915

Text #18

Max Range: 0.8197. Min Range: -0.8197

Max Act: 0.5874. Min Act: -0.0000

Data Index: 1355812 (C4 (Web Text))

Max Activating Token Index: 294

Text #19

Max Range: 0.8197. Min Range: -0.8197

Max Act: 0.5660. Min Act: -0.0001

Data Index: 173397 (C4 (Web Text))

Max Activating Token Index: 618