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

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

Neuron 2639 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: 0.4486. Min Range: -0.4486

Max Act: 0.4386. Min Act: -0.0000

Data Index: 1391060 (Python Code)

Max Activating Token Index: 228

Text #1

Max Range: 0.4486. Min Range: -0.4486

Max Act: 0.4486. Min Act: -0.0000

Data Index: 526878 (C4 (Web Text))

Max Activating Token Index: 570

Text #2

Max Range: 0.4486. Min Range: -0.4486

Max Act: 0.4017. Min Act: -0.0000

Data Index: 1624639 (Python Code)

Max Activating Token Index: 878

Text #3

Max Range: 0.4486. Min Range: -0.4486

Max Act: 0.3765. Min Act: -0.0000

Data Index: 217715 (C4 (Web Text))

Max Activating Token Index: 294

Text #4

Max Range: 0.4486. Min Range: -0.4486

Max Act: 0.3798. Min Act: -0.0000

Data Index: 1416423 (Python Code)

Max Activating Token Index: 560

Text #5

Max Range: 0.4486. Min Range: -0.4486

Max Act: 0.3624. Min Act: -0.0000

Data Index: 1593919 (Python Code)

Max Activating Token Index: 364

Text #6

Max Range: 0.4486. Min Range: -0.4486

Max Act: 0.3640. Min Act: -0.0000

Data Index: 1427122 (Python Code)

Max Activating Token Index: 154

Text #7

Max Range: 0.4486. Min Range: -0.4486

Max Act: 0.3364. Min Act: -0.0000

Data Index: 1446475 (Python Code)

Max Activating Token Index: 336

Text #8

Max Range: 0.4486. Min Range: -0.4486

Max Act: 0.3355. Min Act: -0.0000

Data Index: 1563890 (Python Code)

Max Activating Token Index: 227

Text #9

Max Range: 0.4486. Min Range: -0.4486

Max Act: 0.3280. Min Act: -0.0000

Data Index: 576186 (C4 (Web Text))

Max Activating Token Index: 559

Text #10

Max Range: 0.4486. Min Range: -0.4486

Max Act: 0.3003. Min Act: -0.0000

Data Index: 1647542 (Python Code)

Max Activating Token Index: 219

Text #11

Max Range: 0.4486. Min Range: -0.4486

Max Act: 0.3228. Min Act: -0.0000

Data Index: 594713 (C4 (Web Text))

Max Activating Token Index: 993

Text #12

Max Range: 0.4486. Min Range: -0.4486

Max Act: 0.3258. Min Act: -0.0000

Data Index: 633524 (C4 (Web Text))

Max Activating Token Index: 530

Text #13

Max Range: 0.4486. Min Range: -0.4486

Max Act: 0.3022. Min Act: -0.0000

Data Index: 494804 (C4 (Web Text))

Max Activating Token Index: 850

Text #14

Max Range: 0.4486. Min Range: -0.4486

Max Act: 0.2953. Min Act: -0.0000

Data Index: 778197 (C4 (Web Text))

Max Activating Token Index: 344

Text #15

Max Range: 0.4486. Min Range: -0.4486

Max Act: 0.2978. Min Act: -0.0000

Data Index: 1482859 (Python Code)

Max Activating Token Index: 415

Text #16

Max Range: 0.4486. Min Range: -0.4486

Max Act: 0.3139. Min Act: -0.0000

Data Index: 1520188 (Python Code)

Max Activating Token Index: 431

Text #17

Max Range: 0.4486. Min Range: -0.4486

Max Act: 0.2988. Min Act: -0.0000

Data Index: 1460904 (Python Code)

Max Activating Token Index: 629

Text #18

Max Range: 0.4486. Min Range: -0.4486

Max Act: 0.3005. Min Act: -0.0000

Data Index: 1387485 (Python Code)

Max Activating Token Index: 86

Text #19

Max Range: 0.4486. Min Range: -0.4486

Max Act: 0.3081. Min Act: -0.0000

Data Index: 681055 (C4 (Web Text))

Max Activating Token Index: 342