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

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

Neuron 1423 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: 1.5370. Min Range: -1.5370

Max Act: 1.4837. Min Act: -0.0000

Data Index: 407413 (C4 (Web Text))

Max Activating Token Index: 688

Text #1

Max Range: 1.5370. Min Range: -1.5370

Max Act: 1.5370. Min Act: -0.0000

Data Index: 92371 (C4 (Web Text))

Max Activating Token Index: 642

Text #2

Max Range: 1.5370. Min Range: -1.5370

Max Act: 1.3269. Min Act: -0.0000

Data Index: 349747 (C4 (Web Text))

Max Activating Token Index: 714

Text #3

Max Range: 1.5370. Min Range: -1.5370

Max Act: 1.3920. Min Act: -0.0000

Data Index: 389378 (C4 (Web Text))

Max Activating Token Index: 134

Text #4

Max Range: 1.5370. Min Range: -1.5370

Max Act: 1.2880. Min Act: -0.0000

Data Index: 52535 (C4 (Web Text))

Max Activating Token Index: 294

Text #5

Max Range: 1.5370. Min Range: -1.5370

Max Act: 1.2425. Min Act: -0.0000

Data Index: 688344 (C4 (Web Text))

Max Activating Token Index: 858

Text #6

Max Range: 1.5370. Min Range: -1.5370

Max Act: 1.2507. Min Act: -0.0000

Data Index: 546744 (C4 (Web Text))

Max Activating Token Index: 286

Text #7

Max Range: 1.5370. Min Range: -1.5370

Max Act: 1.0817. Min Act: -0.0000

Data Index: 147985 (C4 (Web Text))

Max Activating Token Index: 819

Text #8

Max Range: 1.5370. Min Range: -1.5370

Max Act: 1.1671. Min Act: -0.0000

Data Index: 760707 (C4 (Web Text))

Max Activating Token Index: 531

Text #9

Max Range: 1.5370. Min Range: -1.5370

Max Act: 1.0239. Min Act: -0.0000

Data Index: 1444577 (Python Code)

Max Activating Token Index: 796

Text #10

Max Range: 1.5370. Min Range: -1.5370

Max Act: 1.0469. Min Act: -0.0000

Data Index: 44863 (C4 (Web Text))

Max Activating Token Index: 194

Text #11

Max Range: 1.5370. Min Range: -1.5370

Max Act: 1.0654. Min Act: -0.0000

Data Index: 1072860 (C4 (Web Text))

Max Activating Token Index: 455

Text #12

Max Range: 1.5370. Min Range: -1.5370

Max Act: 1.0418. Min Act: -0.0000

Data Index: 1558078 (Python Code)

Max Activating Token Index: 390

Text #13

Max Range: 1.5370. Min Range: -1.5370

Max Act: 0.9608. Min Act: -0.0000

Data Index: 747158 (C4 (Web Text))

Max Activating Token Index: 737

Text #14

Max Range: 1.5370. Min Range: -1.5370

Max Act: 1.0870. Min Act: -0.0000

Data Index: 315569 (C4 (Web Text))

Max Activating Token Index: 633

Text #15

Max Range: 1.5370. Min Range: -1.5370

Max Act: 0.8969. Min Act: -0.0000

Data Index: 448021 (C4 (Web Text))

Max Activating Token Index: 783

Text #16

Max Range: 1.5370. Min Range: -1.5370

Max Act: 0.8841. Min Act: -0.0000

Data Index: 1329858 (C4 (Web Text))

Max Activating Token Index: 703

Text #17

Max Range: 1.5370. Min Range: -1.5370

Max Act: 0.9697. Min Act: -0.0000

Data Index: 847867 (C4 (Web Text))

Max Activating Token Index: 447

Text #18

Max Range: 1.5370. Min Range: -1.5370

Max Act: 0.9037. Min Act: -0.0000

Data Index: 671140 (C4 (Web Text))

Max Activating Token Index: 630

Text #19

Max Range: 1.5370. Min Range: -1.5370

Max Act: 0.8467. Min Act: -0.0000

Data Index: 410626 (C4 (Web Text))

Max Activating Token Index: 914