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

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

Neuron 3853 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: 0.5536. Min Range: -0.5536

Max Act: 0.5536. Min Act: -0.0000

Data Index: 372884 (C4 (Web Text))

Max Activating Token Index: 501

Text #1

Max Range: 0.5536. Min Range: -0.5536

Max Act: 0.5373. Min Act: -0.0000

Data Index: 470261 (C4 (Web Text))

Max Activating Token Index: 567

Text #2

Max Range: 0.5536. Min Range: -0.5536

Max Act: 0.5247. Min Act: -0.0000

Data Index: 57678 (C4 (Web Text))

Max Activating Token Index: 383

Text #3

Max Range: 0.5536. Min Range: -0.5536

Max Act: 0.5167. Min Act: -0.0000

Data Index: 511291 (C4 (Web Text))

Max Activating Token Index: 707

Text #4

Max Range: 0.5536. Min Range: -0.5536

Max Act: 0.4967. Min Act: -0.0000

Data Index: 331504 (C4 (Web Text))

Max Activating Token Index: 626

Text #5

Max Range: 0.5536. Min Range: -0.5536

Max Act: 0.4661. Min Act: -0.0000

Data Index: 450235 (C4 (Web Text))

Max Activating Token Index: 258

Text #6

Max Range: 0.5536. Min Range: -0.5536

Max Act: 0.4843. Min Act: -0.0000

Data Index: 851238 (C4 (Web Text))

Max Activating Token Index: 228

Text #7

Max Range: 0.5536. Min Range: -0.5536

Max Act: 0.5126. Min Act: -0.0000

Data Index: 486953 (C4 (Web Text))

Max Activating Token Index: 603

Text #8

Max Range: 0.5536. Min Range: -0.5536

Max Act: 0.4764. Min Act: -0.0000

Data Index: 443498 (C4 (Web Text))

Max Activating Token Index: 572

Text #9

Max Range: 0.5536. Min Range: -0.5536

Max Act: 0.4564. Min Act: -0.0000

Data Index: 1303575 (C4 (Web Text))

Max Activating Token Index: 579

Text #10

Max Range: 0.5536. Min Range: -0.5536

Max Act: 0.4435. Min Act: -0.0000

Data Index: 205266 (C4 (Web Text))

Max Activating Token Index: 749

Text #11

Max Range: 0.5536. Min Range: -0.5536

Max Act: 0.4742. Min Act: -0.0000

Data Index: 255980 (C4 (Web Text))

Max Activating Token Index: 778

Text #12

Max Range: 0.5536. Min Range: -0.5536

Max Act: 0.4045. Min Act: -0.0000

Data Index: 903432 (C4 (Web Text))

Max Activating Token Index: 284

Text #13

Max Range: 0.5536. Min Range: -0.5536

Max Act: 0.4605. Min Act: -0.0000

Data Index: 742872 (C4 (Web Text))

Max Activating Token Index: 203

Text #14

Max Range: 0.5536. Min Range: -0.5536

Max Act: 0.4288. Min Act: -0.0000

Data Index: 934057 (C4 (Web Text))

Max Activating Token Index: 414

Text #15

Max Range: 0.5536. Min Range: -0.5536

Max Act: 0.4409. Min Act: -0.0000

Data Index: 1215240 (C4 (Web Text))

Max Activating Token Index: 866

Text #16

Max Range: 0.5536. Min Range: -0.5536

Max Act: 0.4373. Min Act: -0.0000

Data Index: 401310 (C4 (Web Text))

Max Activating Token Index: 123

Text #17

Max Range: 0.5536. Min Range: -0.5536

Max Act: 0.4234. Min Act: -0.0000

Data Index: 847048 (C4 (Web Text))

Max Activating Token Index: 799

Text #18

Max Range: 0.5536. Min Range: -0.5536

Max Act: 0.4096. Min Act: -0.0000

Data Index: 196886 (C4 (Web Text))

Max Activating Token Index: 598

Text #19

Max Range: 0.5536. Min Range: -0.5536

Max Act: 0.4323. Min Act: -0.0000

Data Index: 1080110 (C4 (Web Text))

Max Activating Token Index: 658