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

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

Neuron 5660 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5209. Min Range: -0.5209

Max Act: 0.5209. Min Act: -0.0000

Data Index: 622284 (C4 (Web Text))

Max Activating Token Index: 656

Text #1

Max Range: 0.5209. Min Range: -0.5209

Max Act: 0.4712. Min Act: -0.0000

Data Index: 658150 (C4 (Web Text))

Max Activating Token Index: 250

Text #2

Max Range: 0.5209. Min Range: -0.5209

Max Act: 0.4317. Min Act: -0.0000

Data Index: 329109 (C4 (Web Text))

Max Activating Token Index: 532

Text #3

Max Range: 0.5209. Min Range: -0.5209

Max Act: 0.4847. Min Act: -0.0000

Data Index: 195701 (C4 (Web Text))

Max Activating Token Index: 362

Text #4

Max Range: 0.5209. Min Range: -0.5209

Max Act: 0.4516. Min Act: -0.0000

Data Index: 806308 (C4 (Web Text))

Max Activating Token Index: 601

Text #5

Max Range: 0.5209. Min Range: -0.5209

Max Act: 0.4482. Min Act: -0.0000

Data Index: 229087 (C4 (Web Text))

Max Activating Token Index: 247

Text #6

Max Range: 0.5209. Min Range: -0.5209

Max Act: 0.4125. Min Act: -0.0000

Data Index: 456533 (C4 (Web Text))

Max Activating Token Index: 517

Text #7

Max Range: 0.5209. Min Range: -0.5209

Max Act: 0.4009. Min Act: -0.0000

Data Index: 278877 (C4 (Web Text))

Max Activating Token Index: 537

Text #8

Max Range: 0.5209. Min Range: -0.5209

Max Act: 0.4068. Min Act: -0.0000

Data Index: 907719 (C4 (Web Text))

Max Activating Token Index: 478

Text #9

Max Range: 0.5209. Min Range: -0.5209

Max Act: 0.3950. Min Act: -0.0000

Data Index: 327592 (C4 (Web Text))

Max Activating Token Index: 553

Text #10

Max Range: 0.5209. Min Range: -0.5209

Max Act: 0.3685. Min Act: -0.0000

Data Index: 223559 (C4 (Web Text))

Max Activating Token Index: 43

Text #11

Max Range: 0.5209. Min Range: -0.5209

Max Act: 0.3853. Min Act: -0.0000

Data Index: 413347 (C4 (Web Text))

Max Activating Token Index: 330

Text #12

Max Range: 0.5209. Min Range: -0.5209

Max Act: 0.3850. Min Act: -0.0000

Data Index: 1183944 (C4 (Web Text))

Max Activating Token Index: 476

Text #13

Max Range: 0.5209. Min Range: -0.5209

Max Act: 0.3697. Min Act: -0.0000

Data Index: 525724 (C4 (Web Text))

Max Activating Token Index: 721

Text #14

Max Range: 0.5209. Min Range: -0.5209

Max Act: 0.3955. Min Act: -0.0000

Data Index: 497960 (C4 (Web Text))

Max Activating Token Index: 194

Text #15

Max Range: 0.5209. Min Range: -0.5209

Max Act: 0.3427. Min Act: -0.0000

Data Index: 445278 (C4 (Web Text))

Max Activating Token Index: 710

Text #16

Max Range: 0.5209. Min Range: -0.5209

Max Act: 0.3559. Min Act: -0.0000

Data Index: 43677 (C4 (Web Text))

Max Activating Token Index: 53

Text #17

Max Range: 0.5209. Min Range: -0.5209

Max Act: 0.3118. Min Act: -0.0000

Data Index: 300071 (C4 (Web Text))

Max Activating Token Index: 35

Text #18

Max Range: 0.5209. Min Range: -0.5209

Max Act: 0.3497. Min Act: -0.0000

Data Index: 1283362 (C4 (Web Text))

Max Activating Token Index: 596

Text #19

Max Range: 0.5209. Min Range: -0.5209

Max Act: 0.3413. Min Act: -0.0000

Data Index: 1278932 (C4 (Web Text))

Max Activating Token Index: 491