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

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

Neuron 1458 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7292. Min Range: -0.7292

Max Act: 0.7292. Min Act: -0.0000

Data Index: 295088 (C4 (Web Text))

Max Activating Token Index: 315

Text #1

Max Range: 0.7292. Min Range: -0.7292

Max Act: 0.6852. Min Act: 0.0000

Data Index: 900363 (C4 (Web Text))

Max Activating Token Index: 81

Text #2

Max Range: 0.7292. Min Range: -0.7292

Max Act: 0.6798. Min Act: -0.0000

Data Index: 140827 (C4 (Web Text))

Max Activating Token Index: 558

Text #3

Max Range: 0.7292. Min Range: -0.7292

Max Act: 0.6609. Min Act: -0.0000

Data Index: 1346576 (C4 (Web Text))

Max Activating Token Index: 159

Text #4

Max Range: 0.7292. Min Range: -0.7292

Max Act: 0.6089. Min Act: -0.0000

Data Index: 1122472 (C4 (Web Text))

Max Activating Token Index: 617

Text #5

Max Range: 0.7292. Min Range: -0.7292

Max Act: 0.6281. Min Act: -0.0000

Data Index: 668020 (C4 (Web Text))

Max Activating Token Index: 1016

Text #6

Max Range: 0.7292. Min Range: -0.7292

Max Act: 0.6023. Min Act: -0.0000

Data Index: 327230 (C4 (Web Text))

Max Activating Token Index: 513

Text #7

Max Range: 0.7292. Min Range: -0.7292

Max Act: 0.6275. Min Act: -0.0000

Data Index: 992569 (C4 (Web Text))

Max Activating Token Index: 825

Text #8

Max Range: 0.7292. Min Range: -0.7292

Max Act: 0.5534. Min Act: 0.0000

Data Index: 920562 (C4 (Web Text))

Max Activating Token Index: 961

Text #9

Max Range: 0.7292. Min Range: -0.7292

Max Act: 0.5330. Min Act: 0.0000

Data Index: 1013995 (C4 (Web Text))

Max Activating Token Index: 633

Text #10

Max Range: 0.7292. Min Range: -0.7292

Max Act: 0.5034. Min Act: -0.0000

Data Index: 1355185 (C4 (Web Text))

Max Activating Token Index: 759

Text #11

Max Range: 0.7292. Min Range: -0.7292

Max Act: 0.5388. Min Act: -0.0000

Data Index: 600307 (C4 (Web Text))

Max Activating Token Index: 439

Text #12

Max Range: 0.7292. Min Range: -0.7292

Max Act: 0.5132. Min Act: -0.0000

Data Index: 743858 (C4 (Web Text))

Max Activating Token Index: 121

Text #13

Max Range: 0.7292. Min Range: -0.7292

Max Act: 0.5478. Min Act: -0.0000

Data Index: 474218 (C4 (Web Text))

Max Activating Token Index: 374

Text #14

Max Range: 0.7292. Min Range: -0.7292

Max Act: 0.5090. Min Act: 0.0000

Data Index: 441758 (C4 (Web Text))

Max Activating Token Index: 447

Text #15

Max Range: 0.7292. Min Range: -0.7292

Max Act: 0.5107. Min Act: -0.0000

Data Index: 1029966 (C4 (Web Text))

Max Activating Token Index: 575

Text #16

Max Range: 0.7292. Min Range: -0.7292

Max Act: 0.5004. Min Act: 0.0000

Data Index: 556827 (C4 (Web Text))

Max Activating Token Index: 483

Text #17

Max Range: 0.7292. Min Range: -0.7292

Max Act: 0.4906. Min Act: -0.0000

Data Index: 1266448 (C4 (Web Text))

Max Activating Token Index: 356

Text #18

Max Range: 0.7292. Min Range: -0.7292

Max Act: 0.4960. Min Act: 0.0000

Data Index: 990768 (C4 (Web Text))

Max Activating Token Index: 584

Text #19

Max Range: 0.7292. Min Range: -0.7292

Max Act: 0.4955. Min Act: -0.0000

Data Index: 942906 (C4 (Web Text))

Max Activating Token Index: 930