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

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

Neuron 2015 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5748. Min Range: -0.5748

Max Act: 0.5748. Min Act: -0.0000

Data Index: 289440 (C4 (Web Text))

Max Activating Token Index: 40

Text #1

Max Range: 0.5748. Min Range: -0.5748

Max Act: 0.5717. Min Act: -0.0000

Data Index: 966394 (C4 (Web Text))

Max Activating Token Index: 224

Text #2

Max Range: 0.5748. Min Range: -0.5748

Max Act: 0.4679. Min Act: -0.0000

Data Index: 562919 (C4 (Web Text))

Max Activating Token Index: 842

Text #3

Max Range: 0.5748. Min Range: -0.5748

Max Act: 0.4804. Min Act: -0.0000

Data Index: 361535 (C4 (Web Text))

Max Activating Token Index: 209

Text #4

Max Range: 0.5748. Min Range: -0.5748

Max Act: 0.4581. Min Act: -0.0000

Data Index: 467477 (C4 (Web Text))

Max Activating Token Index: 10

Text #5

Max Range: 0.5748. Min Range: -0.5748

Max Act: 0.4270. Min Act: -0.0000

Data Index: 695659 (C4 (Web Text))

Max Activating Token Index: 314

Text #6

Max Range: 0.5748. Min Range: -0.5748

Max Act: 0.4538. Min Act: -0.0000

Data Index: 719955 (C4 (Web Text))

Max Activating Token Index: 264

Text #7

Max Range: 0.5748. Min Range: -0.5748

Max Act: 0.4088. Min Act: -0.0000

Data Index: 286110 (C4 (Web Text))

Max Activating Token Index: 22

Text #8

Max Range: 0.5748. Min Range: -0.5748

Max Act: 0.4038. Min Act: -0.0000

Data Index: 151456 (C4 (Web Text))

Max Activating Token Index: 5

Text #9

Max Range: 0.5748. Min Range: -0.5748

Max Act: 0.4117. Min Act: -0.0000

Data Index: 517906 (C4 (Web Text))

Max Activating Token Index: 529

Text #10

Max Range: 0.5748. Min Range: -0.5748

Max Act: 0.4209. Min Act: -0.0000

Data Index: 596363 (C4 (Web Text))

Max Activating Token Index: 7

Text #11

Max Range: 0.5748. Min Range: -0.5748

Max Act: 0.4061. Min Act: -0.0000

Data Index: 870033 (C4 (Web Text))

Max Activating Token Index: 465

Text #12

Max Range: 0.5748. Min Range: -0.5748

Max Act: 0.3887. Min Act: -0.0000

Data Index: 1357772 (C4 (Web Text))

Max Activating Token Index: 530

Text #13

Max Range: 0.5748. Min Range: -0.5748

Max Act: 0.3750. Min Act: -0.0000

Data Index: 72664 (C4 (Web Text))

Max Activating Token Index: 946

Text #14

Max Range: 0.5748. Min Range: -0.5748

Max Act: 0.3654. Min Act: -0.0000

Data Index: 431678 (C4 (Web Text))

Max Activating Token Index: 817

Text #15

Max Range: 0.5748. Min Range: -0.5748

Max Act: 0.3882. Min Act: -0.0000

Data Index: 1133140 (C4 (Web Text))

Max Activating Token Index: 10

Text #16

Max Range: 0.5748. Min Range: -0.5748

Max Act: 0.3643. Min Act: -0.0000

Data Index: 924761 (C4 (Web Text))

Max Activating Token Index: 8

Text #17

Max Range: 0.5748. Min Range: -0.5748

Max Act: 0.3394. Min Act: -0.0000

Data Index: 727524 (C4 (Web Text))

Max Activating Token Index: 622

Text #18

Max Range: 0.5748. Min Range: -0.5748

Max Act: 0.3730. Min Act: -0.0000

Data Index: 364682 (C4 (Web Text))

Max Activating Token Index: 17

Text #19

Max Range: 0.5748. Min Range: -0.5748

Max Act: 0.3693. Min Act: -0.0000

Data Index: 46463 (C4 (Web Text))

Max Activating Token Index: 916