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

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

Neuron 914 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2375. Min Range: -1.2375

Max Act: 1.2375. Min Act: -0.0000

Data Index: 1104872 (C4 (Web Text))

Max Activating Token Index: 985

Text #1

Max Range: 1.2375. Min Range: -1.2375

Max Act: 0.9769. Min Act: -0.0000

Data Index: 1201489 (C4 (Web Text))

Max Activating Token Index: 351

Text #2

Max Range: 1.2375. Min Range: -1.2375

Max Act: 0.9239. Min Act: -0.0000

Data Index: 1163353 (C4 (Web Text))

Max Activating Token Index: 532

Text #3

Max Range: 1.2375. Min Range: -1.2375

Max Act: 0.9386. Min Act: -0.0000

Data Index: 1224605 (C4 (Web Text))

Max Activating Token Index: 618

Text #4

Max Range: 1.2375. Min Range: -1.2375

Max Act: 0.8755. Min Act: -0.0000

Data Index: 205337 (C4 (Web Text))

Max Activating Token Index: 129

Text #5

Max Range: 1.2375. Min Range: -1.2375

Max Act: 0.8488. Min Act: -0.0000

Data Index: 1324443 (C4 (Web Text))

Max Activating Token Index: 263

Text #6

Max Range: 1.2375. Min Range: -1.2375

Max Act: 0.8263. Min Act: -0.0000

Data Index: 420853 (C4 (Web Text))

Max Activating Token Index: 382

Text #7

Max Range: 1.2375. Min Range: -1.2375

Max Act: 0.7990. Min Act: -0.0000

Data Index: 1373219 (Python Code)

Max Activating Token Index: 52

Text #8

Max Range: 1.2375. Min Range: -1.2375

Max Act: 0.7918. Min Act: -0.0000

Data Index: 613958 (C4 (Web Text))

Max Activating Token Index: 51

Text #9

Max Range: 1.2375. Min Range: -1.2375

Max Act: 0.7798. Min Act: -0.0000

Data Index: 1105640 (C4 (Web Text))

Max Activating Token Index: 549

Text #10

Max Range: 1.2375. Min Range: -1.2375

Max Act: 0.7771. Min Act: -0.0000

Data Index: 188157 (C4 (Web Text))

Max Activating Token Index: 465

Text #11

Max Range: 1.2375. Min Range: -1.2375

Max Act: 0.8007. Min Act: -0.0000

Data Index: 1011903 (C4 (Web Text))

Max Activating Token Index: 605

Text #12

Max Range: 1.2375. Min Range: -1.2375

Max Act: 0.7786. Min Act: -0.0000

Data Index: 1598062 (Python Code)

Max Activating Token Index: 23

Text #13

Max Range: 1.2375. Min Range: -1.2375

Max Act: 0.7309. Min Act: -0.0000

Data Index: 1174322 (C4 (Web Text))

Max Activating Token Index: 213

Text #14

Max Range: 1.2375. Min Range: -1.2375

Max Act: 0.7276. Min Act: -0.0000

Data Index: 1539050 (Python Code)

Max Activating Token Index: 382

Text #15

Max Range: 1.2375. Min Range: -1.2375

Max Act: 0.7248. Min Act: -0.0000

Data Index: 1548866 (Python Code)

Max Activating Token Index: 109

Text #16

Max Range: 1.2375. Min Range: -1.2375

Max Act: 0.6946. Min Act: -0.0000

Data Index: 1037467 (C4 (Web Text))

Max Activating Token Index: 682

Text #17

Max Range: 1.2375. Min Range: -1.2375

Max Act: 0.6755. Min Act: -0.0000

Data Index: 545248 (C4 (Web Text))

Max Activating Token Index: 738

Text #18

Max Range: 1.2375. Min Range: -1.2375

Max Act: 0.6911. Min Act: -0.0000

Data Index: 1541675 (Python Code)

Max Activating Token Index: 998

Text #19

Max Range: 1.2375. Min Range: -1.2375

Max Act: 0.7512. Min Act: -0.0000

Data Index: 917055 (C4 (Web Text))

Max Activating Token Index: 622