Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 896 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.6248. Min Range: -1.6248

Max Act: 1.6248. Min Act: -0.0001

Data Index: 548868 (C4 (Web Text))

Max Activating Token Index: 387

Text #1

Max Range: 1.6248. Min Range: -1.6248

Max Act: 1.2868. Min Act: -0.0001

Data Index: 685635 (C4 (Web Text))

Max Activating Token Index: 464

Text #2

Max Range: 1.6248. Min Range: -1.6248

Max Act: 1.2111. Min Act: -0.0001

Data Index: 228576 (C4 (Web Text))

Max Activating Token Index: 117

Text #3

Max Range: 1.6248. Min Range: -1.6248

Max Act: 1.2032. Min Act: -0.0001

Data Index: 1115019 (C4 (Web Text))

Max Activating Token Index: 80

Text #4

Max Range: 1.6248. Min Range: -1.6248

Max Act: 1.1580. Min Act: -0.0001

Data Index: 914974 (C4 (Web Text))

Max Activating Token Index: 74

Text #5

Max Range: 1.6248. Min Range: -1.6248

Max Act: 1.0999. Min Act: -0.0001

Data Index: 1115084 (C4 (Web Text))

Max Activating Token Index: 720

Text #6

Max Range: 1.6248. Min Range: -1.6248

Max Act: 1.0967. Min Act: -0.0001

Data Index: 1090579 (C4 (Web Text))

Max Activating Token Index: 536

Text #7

Max Range: 1.6248. Min Range: -1.6248

Max Act: 1.1959. Min Act: -0.0001

Data Index: 1310128 (C4 (Web Text))

Max Activating Token Index: 295

Text #8

Max Range: 1.6248. Min Range: -1.6248

Max Act: 1.0686. Min Act: -0.0001

Data Index: 777376 (C4 (Web Text))

Max Activating Token Index: 728

Text #9

Max Range: 1.6248. Min Range: -1.6248

Max Act: 0.9673. Min Act: -0.0001

Data Index: 871817 (C4 (Web Text))

Max Activating Token Index: 984

Text #10

Max Range: 1.6248. Min Range: -1.6248

Max Act: 1.0672. Min Act: -0.0001

Data Index: 58195 (C4 (Web Text))

Max Activating Token Index: 652

Text #11

Max Range: 1.6248. Min Range: -1.6248

Max Act: 0.9859. Min Act: -0.0001

Data Index: 1545548 (Python Code)

Max Activating Token Index: 616

Text #12

Max Range: 1.6248. Min Range: -1.6248

Max Act: 1.0000. Min Act: -0.0001

Data Index: 7596 (C4 (Web Text))

Max Activating Token Index: 685

Text #13

Max Range: 1.6248. Min Range: -1.6248

Max Act: 0.9662. Min Act: -0.0001

Data Index: 836708 (C4 (Web Text))

Max Activating Token Index: 435

Text #14

Max Range: 1.6248. Min Range: -1.6248

Max Act: 0.9374. Min Act: -0.0001

Data Index: 128557 (C4 (Web Text))

Max Activating Token Index: 489

Text #15

Max Range: 1.6248. Min Range: -1.6248

Max Act: 0.9243. Min Act: -0.0001

Data Index: 253470 (C4 (Web Text))

Max Activating Token Index: 36

Text #16

Max Range: 1.6248. Min Range: -1.6248

Max Act: 0.9690. Min Act: -0.0001

Data Index: 1282515 (C4 (Web Text))

Max Activating Token Index: 298

Text #17

Max Range: 1.6248. Min Range: -1.6248

Max Act: 0.9264. Min Act: -0.0001

Data Index: 1027393 (C4 (Web Text))

Max Activating Token Index: 811

Text #18

Max Range: 1.6248. Min Range: -1.6248

Max Act: 0.8621. Min Act: -0.0001

Data Index: 648687 (C4 (Web Text))

Max Activating Token Index: 685

Text #19

Max Range: 1.6248. Min Range: -1.6248

Max Act: 0.9497. Min Act: -0.0001

Data Index: 600484 (C4 (Web Text))

Max Activating Token Index: 381