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

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

Neuron 2427 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6624. Min Range: -0.6624

Max Act: 0.6624. Min Act: -0.0000

Data Index: 668588 (C4 (Web Text))

Max Activating Token Index: 387

Text #1

Max Range: 0.6624. Min Range: -0.6624

Max Act: 0.6041. Min Act: -0.0000

Data Index: 281010 (C4 (Web Text))

Max Activating Token Index: 795

Text #2

Max Range: 0.6624. Min Range: -0.6624

Max Act: 0.6226. Min Act: -0.0000

Data Index: 153985 (C4 (Web Text))

Max Activating Token Index: 738

Text #3

Max Range: 0.6624. Min Range: -0.6624

Max Act: 0.6182. Min Act: -0.0000

Data Index: 684156 (C4 (Web Text))

Max Activating Token Index: 702

Text #4

Max Range: 0.6624. Min Range: -0.6624

Max Act: 0.5255. Min Act: -0.0000

Data Index: 778373 (C4 (Web Text))

Max Activating Token Index: 675

Text #5

Max Range: 0.6624. Min Range: -0.6624

Max Act: 0.5669. Min Act: -0.0000

Data Index: 946741 (C4 (Web Text))

Max Activating Token Index: 1014

Text #6

Max Range: 0.6624. Min Range: -0.6624

Max Act: 0.4816. Min Act: -0.0000

Data Index: 915286 (C4 (Web Text))

Max Activating Token Index: 925

Text #7

Max Range: 0.6624. Min Range: -0.6624

Max Act: 0.4599. Min Act: -0.0000

Data Index: 354774 (C4 (Web Text))

Max Activating Token Index: 822

Text #8

Max Range: 0.6624. Min Range: -0.6624

Max Act: 0.4943. Min Act: -0.0000

Data Index: 153626 (C4 (Web Text))

Max Activating Token Index: 420

Text #9

Max Range: 0.6624. Min Range: -0.6624

Max Act: 0.4780. Min Act: -0.0000

Data Index: 305400 (C4 (Web Text))

Max Activating Token Index: 818

Text #10

Max Range: 0.6624. Min Range: -0.6624

Max Act: 0.4921. Min Act: -0.0000

Data Index: 314167 (C4 (Web Text))

Max Activating Token Index: 961

Text #11

Max Range: 0.6624. Min Range: -0.6624

Max Act: 0.5487. Min Act: -0.0000

Data Index: 634874 (C4 (Web Text))

Max Activating Token Index: 1016

Text #12

Max Range: 0.6624. Min Range: -0.6624

Max Act: 0.4615. Min Act: -0.0000

Data Index: 99045 (C4 (Web Text))

Max Activating Token Index: 472

Text #13

Max Range: 0.6624. Min Range: -0.6624

Max Act: 0.3731. Min Act: -0.0000

Data Index: 1037900 (C4 (Web Text))

Max Activating Token Index: 572

Text #14

Max Range: 0.6624. Min Range: -0.6624

Max Act: 0.3951. Min Act: -0.0000

Data Index: 663886 (C4 (Web Text))

Max Activating Token Index: 697

Text #15

Max Range: 0.6624. Min Range: -0.6624

Max Act: 0.3880. Min Act: -0.0000

Data Index: 694999 (C4 (Web Text))

Max Activating Token Index: 951

Text #16

Max Range: 0.6624. Min Range: -0.6624

Max Act: 0.3797. Min Act: -0.0000

Data Index: 495072 (C4 (Web Text))

Max Activating Token Index: 196

Text #17

Max Range: 0.6624. Min Range: -0.6624

Max Act: 0.4002. Min Act: -0.0000

Data Index: 168665 (C4 (Web Text))

Max Activating Token Index: 298

Text #18

Max Range: 0.6624. Min Range: -0.6624

Max Act: 0.3983. Min Act: -0.0000

Data Index: 630000 (C4 (Web Text))

Max Activating Token Index: 390

Text #19

Max Range: 0.6624. Min Range: -0.6624

Max Act: 0.3878. Min Act: -0.0000

Data Index: 172721 (C4 (Web Text))

Max Activating Token Index: 319