Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1022 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.5220. Min Range: -0.5220

Max Act: 0.5220. Min Act: -0.0002

Data Index: 1303964 (C4 (Web Text))

Max Activating Token Index: 582

Text #1

Max Range: 0.5220. Min Range: -0.5220

Max Act: 0.4706. Min Act: -0.0002

Data Index: 1201918 (C4 (Web Text))

Max Activating Token Index: 516

Text #2

Max Range: 0.5220. Min Range: -0.5220

Max Act: 0.4508. Min Act: -0.0002

Data Index: 17848 (C4 (Web Text))

Max Activating Token Index: 730

Text #3

Max Range: 0.5220. Min Range: -0.5220

Max Act: 0.4761. Min Act: -0.0002

Data Index: 364702 (C4 (Web Text))

Max Activating Token Index: 192

Text #4

Max Range: 0.5220. Min Range: -0.5220

Max Act: 0.4846. Min Act: -0.0002

Data Index: 382273 (C4 (Web Text))

Max Activating Token Index: 134

Text #5

Max Range: 0.5220. Min Range: -0.5220

Max Act: 0.4479. Min Act: -0.0002

Data Index: 194165 (C4 (Web Text))

Max Activating Token Index: 213

Text #6

Max Range: 0.5220. Min Range: -0.5220

Max Act: 0.4608. Min Act: -0.0002

Data Index: 67030 (C4 (Web Text))

Max Activating Token Index: 54

Text #7

Max Range: 0.5220. Min Range: -0.5220

Max Act: 0.4399. Min Act: -0.0002

Data Index: 60077 (C4 (Web Text))

Max Activating Token Index: 461

Text #8

Max Range: 0.5220. Min Range: -0.5220

Max Act: 0.4186. Min Act: -0.0002

Data Index: 118955 (C4 (Web Text))

Max Activating Token Index: 985

Text #9

Max Range: 0.5220. Min Range: -0.5220

Max Act: 0.4072. Min Act: -0.0002

Data Index: 551190 (C4 (Web Text))

Max Activating Token Index: 537

Text #10

Max Range: 0.5220. Min Range: -0.5220

Max Act: 0.3998. Min Act: -0.0002

Data Index: 956910 (C4 (Web Text))

Max Activating Token Index: 550

Text #11

Max Range: 0.5220. Min Range: -0.5220

Max Act: 0.4291. Min Act: -0.0002

Data Index: 746775 (C4 (Web Text))

Max Activating Token Index: 194

Text #12

Max Range: 0.5220. Min Range: -0.5220

Max Act: 0.4018. Min Act: -0.0002

Data Index: 335496 (C4 (Web Text))

Max Activating Token Index: 669

Text #13

Max Range: 0.5220. Min Range: -0.5220

Max Act: 0.3946. Min Act: -0.0002

Data Index: 1126905 (C4 (Web Text))

Max Activating Token Index: 715

Text #14

Max Range: 0.5220. Min Range: -0.5220

Max Act: 0.4015. Min Act: -0.0002

Data Index: 368127 (C4 (Web Text))

Max Activating Token Index: 704

Text #15

Max Range: 0.5220. Min Range: -0.5220

Max Act: 0.3831. Min Act: -0.0002

Data Index: 740785 (C4 (Web Text))

Max Activating Token Index: 594

Text #16

Max Range: 0.5220. Min Range: -0.5220

Max Act: 0.4216. Min Act: -0.0002

Data Index: 413703 (C4 (Web Text))

Max Activating Token Index: 246

Text #17

Max Range: 0.5220. Min Range: -0.5220

Max Act: 0.4023. Min Act: -0.0002

Data Index: 195531 (C4 (Web Text))

Max Activating Token Index: 1018

Text #18

Max Range: 0.5220. Min Range: -0.5220

Max Act: 0.4009. Min Act: -0.0002

Data Index: 842792 (C4 (Web Text))

Max Activating Token Index: 258

Text #19

Max Range: 0.5220. Min Range: -0.5220

Max Act: 0.4033. Min Act: -0.0002

Data Index: 654772 (C4 (Web Text))

Max Activating Token Index: 390