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

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

Neuron 129 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9748. Min Range: -0.9748

Max Act: 0.9748. Min Act: -0.0000

Data Index: 87170 (C4 (Web Text))

Max Activating Token Index: 882

Text #1

Max Range: 0.9748. Min Range: -0.9748

Max Act: 0.7659. Min Act: -0.0000

Data Index: 209623 (C4 (Web Text))

Max Activating Token Index: 277

Text #2

Max Range: 0.9748. Min Range: -0.9748

Max Act: 0.7906. Min Act: -0.0000

Data Index: 1285224 (C4 (Web Text))

Max Activating Token Index: 320

Text #3

Max Range: 0.9748. Min Range: -0.9748

Max Act: 0.8022. Min Act: -0.0000

Data Index: 965779 (C4 (Web Text))

Max Activating Token Index: 508

Text #4

Max Range: 0.9748. Min Range: -0.9748

Max Act: 0.7550. Min Act: -0.0000

Data Index: 260483 (C4 (Web Text))

Max Activating Token Index: 618

Text #5

Max Range: 0.9748. Min Range: -0.9748

Max Act: 0.6570. Min Act: -0.0000

Data Index: 844907 (C4 (Web Text))

Max Activating Token Index: 948

Text #6

Max Range: 0.9748. Min Range: -0.9748

Max Act: 0.6760. Min Act: -0.0000

Data Index: 299509 (C4 (Web Text))

Max Activating Token Index: 752

Text #7

Max Range: 0.9748. Min Range: -0.9748

Max Act: 0.7256. Min Act: -0.0000

Data Index: 1278381 (C4 (Web Text))

Max Activating Token Index: 790

Text #8

Max Range: 0.9748. Min Range: -0.9748

Max Act: 0.6295. Min Act: -0.0000

Data Index: 337201 (C4 (Web Text))

Max Activating Token Index: 318

Text #9

Max Range: 0.9748. Min Range: -0.9748

Max Act: 0.6853. Min Act: -0.0000

Data Index: 498120 (C4 (Web Text))

Max Activating Token Index: 566

Text #10

Max Range: 0.9748. Min Range: -0.9748

Max Act: 0.6506. Min Act: -0.0000

Data Index: 1197155 (C4 (Web Text))

Max Activating Token Index: 875

Text #11

Max Range: 0.9748. Min Range: -0.9748

Max Act: 0.6448. Min Act: -0.0000

Data Index: 48613 (C4 (Web Text))

Max Activating Token Index: 831

Text #12

Max Range: 0.9748. Min Range: -0.9748

Max Act: 0.6609. Min Act: -0.0000

Data Index: 918162 (C4 (Web Text))

Max Activating Token Index: 251

Text #13

Max Range: 0.9748. Min Range: -0.9748

Max Act: 0.6306. Min Act: -0.0000

Data Index: 762351 (C4 (Web Text))

Max Activating Token Index: 54

Text #14

Max Range: 0.9748. Min Range: -0.9748

Max Act: 0.6235. Min Act: -0.0000

Data Index: 1296154 (C4 (Web Text))

Max Activating Token Index: 14

Text #15

Max Range: 0.9748. Min Range: -0.9748

Max Act: 0.6107. Min Act: -0.0000

Data Index: 771970 (C4 (Web Text))

Max Activating Token Index: 118

Text #16

Max Range: 0.9748. Min Range: -0.9748

Max Act: 0.6893. Min Act: -0.0000

Data Index: 767658 (C4 (Web Text))

Max Activating Token Index: 565

Text #17

Max Range: 0.9748. Min Range: -0.9748

Max Act: 0.5706. Min Act: -0.0000

Data Index: 169556 (C4 (Web Text))

Max Activating Token Index: 316

Text #18

Max Range: 0.9748. Min Range: -0.9748

Max Act: 0.5488. Min Act: -0.0000

Data Index: 572138 (C4 (Web Text))

Max Activating Token Index: 365

Text #19

Max Range: 0.9748. Min Range: -0.9748

Max Act: 0.6110. Min Act: -0.0000

Data Index: 903638 (C4 (Web Text))

Max Activating Token Index: 954