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

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

Neuron 930 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7097. Min Range: -0.7097

Max Act: 0.7097. Min Act: -0.0002

Data Index: 1015555 (C4 (Web Text))

Max Activating Token Index: 1002

Text #1

Max Range: 0.7097. Min Range: -0.7097

Max Act: 0.4784. Min Act: -0.0002

Data Index: 1179612 (C4 (Web Text))

Max Activating Token Index: 297

Text #2

Max Range: 0.7097. Min Range: -0.7097

Max Act: 0.4108. Min Act: -0.0002

Data Index: 293308 (C4 (Web Text))

Max Activating Token Index: 836

Text #3

Max Range: 0.7097. Min Range: -0.7097

Max Act: 0.4532. Min Act: -0.0002

Data Index: 1438846 (Python Code)

Max Activating Token Index: 229

Text #4

Max Range: 0.7097. Min Range: -0.7097

Max Act: 0.5129. Min Act: -0.0002

Data Index: 613026 (C4 (Web Text))

Max Activating Token Index: 27

Text #5

Max Range: 0.7097. Min Range: -0.7097

Max Act: 0.5095. Min Act: -0.0002

Data Index: 515259 (C4 (Web Text))

Max Activating Token Index: 818

Text #6

Max Range: 0.7097. Min Range: -0.7097

Max Act: 0.5263. Min Act: -0.0002

Data Index: 831882 (C4 (Web Text))

Max Activating Token Index: 184

Text #7

Max Range: 0.7097. Min Range: -0.7097

Max Act: 0.4662. Min Act: -0.0002

Data Index: 328256 (C4 (Web Text))

Max Activating Token Index: 543

Text #8

Max Range: 0.7097. Min Range: -0.7097

Max Act: 0.5098. Min Act: -0.0002

Data Index: 209340 (C4 (Web Text))

Max Activating Token Index: 114

Text #9

Max Range: 0.7097. Min Range: -0.7097

Max Act: 0.4317. Min Act: -0.0002

Data Index: 847756 (C4 (Web Text))

Max Activating Token Index: 371

Text #10

Max Range: 0.7097. Min Range: -0.7097

Max Act: 0.4566. Min Act: -0.0002

Data Index: 1643326 (Python Code)

Max Activating Token Index: 66

Text #11

Max Range: 0.7097. Min Range: -0.7097

Max Act: 0.3711. Min Act: -0.0002

Data Index: 1384274 (Python Code)

Max Activating Token Index: 759

Text #12

Max Range: 0.7097. Min Range: -0.7097

Max Act: 0.4548. Min Act: -0.0002

Data Index: 431344 (C4 (Web Text))

Max Activating Token Index: 793

Text #13

Max Range: 0.7097. Min Range: -0.7097

Max Act: 0.4536. Min Act: -0.0002

Data Index: 527034 (C4 (Web Text))

Max Activating Token Index: 9

Text #14

Max Range: 0.7097. Min Range: -0.7097

Max Act: 0.4493. Min Act: -0.0002

Data Index: 1061761 (C4 (Web Text))

Max Activating Token Index: 244

Text #15

Max Range: 0.7097. Min Range: -0.7097

Max Act: 0.4635. Min Act: -0.0002

Data Index: 1378166 (Python Code)

Max Activating Token Index: 153

Text #16

Max Range: 0.7097. Min Range: -0.7097

Max Act: 0.4487. Min Act: -0.0002

Data Index: 397749 (C4 (Web Text))

Max Activating Token Index: 850

Text #17

Max Range: 0.7097. Min Range: -0.7097

Max Act: 0.5076. Min Act: -0.0002

Data Index: 1448825 (Python Code)

Max Activating Token Index: 651

Text #18

Max Range: 0.7097. Min Range: -0.7097

Max Act: 0.4479. Min Act: -0.0002

Data Index: 1108755 (C4 (Web Text))

Max Activating Token Index: 856

Text #19

Max Range: 0.7097. Min Range: -0.7097

Max Act: 0.4859. Min Act: -0.0002

Data Index: 1511209 (Python Code)

Max Activating Token Index: 278