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

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

Neuron 413 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6233. Min Range: -0.6233

Max Act: 0.5799. Min Act: -0.0000

Data Index: 1522476 (Python Code)

Max Activating Token Index: 729

Text #1

Max Range: 0.6233. Min Range: -0.6233

Max Act: 0.6222. Min Act: -0.0000

Data Index: 354805 (C4 (Web Text))

Max Activating Token Index: 345

Text #2

Max Range: 0.6233. Min Range: -0.6233

Max Act: 0.6233. Min Act: -0.0000

Data Index: 1522908 (Python Code)

Max Activating Token Index: 279

Text #3

Max Range: 0.6233. Min Range: -0.6233

Max Act: 0.5765. Min Act: -0.0000

Data Index: 1074022 (C4 (Web Text))

Max Activating Token Index: 263

Text #4

Max Range: 0.6233. Min Range: -0.6233

Max Act: 0.5450. Min Act: -0.0000

Data Index: 593196 (C4 (Web Text))

Max Activating Token Index: 959

Text #5

Max Range: 0.6233. Min Range: -0.6233

Max Act: 0.5300. Min Act: -0.0000

Data Index: 428849 (C4 (Web Text))

Max Activating Token Index: 934

Text #6

Max Range: 0.6233. Min Range: -0.6233

Max Act: 0.5280. Min Act: -0.0000

Data Index: 519797 (C4 (Web Text))

Max Activating Token Index: 183

Text #7

Max Range: 0.6233. Min Range: -0.6233

Max Act: 0.5222. Min Act: -0.0000

Data Index: 252567 (C4 (Web Text))

Max Activating Token Index: 37

Text #8

Max Range: 0.6233. Min Range: -0.6233

Max Act: 0.4960. Min Act: -0.0000

Data Index: 1617094 (Python Code)

Max Activating Token Index: 128

Text #9

Max Range: 0.6233. Min Range: -0.6233

Max Act: 0.4817. Min Act: -0.0000

Data Index: 1044493 (C4 (Web Text))

Max Activating Token Index: 900

Text #10

Max Range: 0.6233. Min Range: -0.6233

Max Act: 0.4793. Min Act: -0.0000

Data Index: 653135 (C4 (Web Text))

Max Activating Token Index: 313

Text #11

Max Range: 0.6233. Min Range: -0.6233

Max Act: 0.4581. Min Act: -0.0000

Data Index: 856110 (C4 (Web Text))

Max Activating Token Index: 143

Text #12

Max Range: 0.6233. Min Range: -0.6233

Max Act: 0.4688. Min Act: -0.0000

Data Index: 677433 (C4 (Web Text))

Max Activating Token Index: 130

Text #13

Max Range: 0.6233. Min Range: -0.6233

Max Act: 0.4707. Min Act: -0.0000

Data Index: 813388 (C4 (Web Text))

Max Activating Token Index: 242

Text #14

Max Range: 0.6233. Min Range: -0.6233

Max Act: 0.4474. Min Act: -0.0000

Data Index: 434638 (C4 (Web Text))

Max Activating Token Index: 769

Text #15

Max Range: 0.6233. Min Range: -0.6233

Max Act: 0.4460. Min Act: -0.0000

Data Index: 267235 (C4 (Web Text))

Max Activating Token Index: 81

Text #16

Max Range: 0.6233. Min Range: -0.6233

Max Act: 0.4696. Min Act: -0.0000

Data Index: 985647 (C4 (Web Text))

Max Activating Token Index: 730

Text #17

Max Range: 0.6233. Min Range: -0.6233

Max Act: 0.4706. Min Act: -0.0000

Data Index: 1027704 (C4 (Web Text))

Max Activating Token Index: 644

Text #18

Max Range: 0.6233. Min Range: -0.6233

Max Act: 0.4099. Min Act: 0.0000

Data Index: 1104626 (C4 (Web Text))

Max Activating Token Index: 119

Text #19

Max Range: 0.6233. Min Range: -0.6233

Max Act: 0.4485. Min Act: -0.0000

Data Index: 213072 (C4 (Web Text))

Max Activating Token Index: 672