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

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

Neuron 5143 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: 0.8809. Min Range: -0.8809

Max Act: 0.8426. Min Act: -0.0001

Data Index: 1028464 (C4 (Web Text))

Max Activating Token Index: 78

Text #1

Max Range: 0.8809. Min Range: -0.8809

Max Act: 0.8074. Min Act: -0.0000

Data Index: 1165730 (C4 (Web Text))

Max Activating Token Index: 214

Text #2

Max Range: 0.8809. Min Range: -0.8809

Max Act: 0.8809. Min Act: -0.0000

Data Index: 1432209 (Python Code)

Max Activating Token Index: 213

Text #3

Max Range: 0.8809. Min Range: -0.8809

Max Act: 0.8253. Min Act: -0.0000

Data Index: 1148269 (C4 (Web Text))

Max Activating Token Index: 163

Text #4

Max Range: 0.8809. Min Range: -0.8809

Max Act: 0.8168. Min Act: -0.0000

Data Index: 1111895 (C4 (Web Text))

Max Activating Token Index: 604

Text #5

Max Range: 0.8809. Min Range: -0.8809

Max Act: 0.7799. Min Act: -0.0000

Data Index: 1396278 (Python Code)

Max Activating Token Index: 569

Text #6

Max Range: 0.8809. Min Range: -0.8809

Max Act: 0.8084. Min Act: -0.0000

Data Index: 1522361 (Python Code)

Max Activating Token Index: 793

Text #7

Max Range: 0.8809. Min Range: -0.8809

Max Act: 0.6668. Min Act: -0.0000

Data Index: 1038970 (C4 (Web Text))

Max Activating Token Index: 923

Text #8

Max Range: 0.8809. Min Range: -0.8809

Max Act: 0.6874. Min Act: -0.0000

Data Index: 189611 (C4 (Web Text))

Max Activating Token Index: 676

Text #9

Max Range: 0.8809. Min Range: -0.8809

Max Act: 0.6801. Min Act: -0.0000

Data Index: 723691 (C4 (Web Text))

Max Activating Token Index: 332

Text #10

Max Range: 0.8809. Min Range: -0.8809

Max Act: 0.6356. Min Act: -0.0000

Data Index: 545609 (C4 (Web Text))

Max Activating Token Index: 410

Text #11

Max Range: 0.8809. Min Range: -0.8809

Max Act: 0.6642. Min Act: -0.0000

Data Index: 396272 (C4 (Web Text))

Max Activating Token Index: 504

Text #12

Max Range: 0.8809. Min Range: -0.8809

Max Act: 0.6323. Min Act: -0.0000

Data Index: 1298721 (C4 (Web Text))

Max Activating Token Index: 334

Text #13

Max Range: 0.8809. Min Range: -0.8809

Max Act: 0.6636. Min Act: -0.0000

Data Index: 92050 (C4 (Web Text))

Max Activating Token Index: 220

Text #14

Max Range: 0.8809. Min Range: -0.8809

Max Act: 0.5750. Min Act: -0.0000

Data Index: 389715 (C4 (Web Text))

Max Activating Token Index: 901

Text #15

Max Range: 0.8809. Min Range: -0.8809

Max Act: 0.5875. Min Act: -0.0000

Data Index: 921796 (C4 (Web Text))

Max Activating Token Index: 179

Text #16

Max Range: 0.8809. Min Range: -0.8809

Max Act: 0.6214. Min Act: -0.0000

Data Index: 1243083 (C4 (Web Text))

Max Activating Token Index: 497

Text #17

Max Range: 0.8809. Min Range: -0.8809

Max Act: 0.6101. Min Act: -0.0000

Data Index: 1458283 (Python Code)

Max Activating Token Index: 436

Text #18

Max Range: 0.8809. Min Range: -0.8809

Max Act: 0.5574. Min Act: -0.0000

Data Index: 935108 (C4 (Web Text))

Max Activating Token Index: 605

Text #19

Max Range: 0.8809. Min Range: -0.8809

Max Act: 0.6207. Min Act: -0.0000

Data Index: 1241296 (C4 (Web Text))

Max Activating Token Index: 661