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

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

Neuron 2147 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5853. Min Range: -0.5853

Max Act: 0.5853. Min Act: -0.0000

Data Index: 1040791 (C4 (Web Text))

Max Activating Token Index: 24

Text #1

Max Range: 0.5853. Min Range: -0.5853

Max Act: 0.4928. Min Act: -0.0000

Data Index: 599392 (C4 (Web Text))

Max Activating Token Index: 576

Text #2

Max Range: 0.5853. Min Range: -0.5853

Max Act: 0.3618. Min Act: -0.0000

Data Index: 1096275 (C4 (Web Text))

Max Activating Token Index: 34

Text #3

Max Range: 0.5853. Min Range: -0.5853

Max Act: 0.3577. Min Act: -0.0000

Data Index: 272165 (C4 (Web Text))

Max Activating Token Index: 665

Text #4

Max Range: 0.5853. Min Range: -0.5853

Max Act: 0.3417. Min Act: -0.0000

Data Index: 408891 (C4 (Web Text))

Max Activating Token Index: 127

Text #5

Max Range: 0.5853. Min Range: -0.5853

Max Act: 0.3302. Min Act: -0.0000

Data Index: 639547 (C4 (Web Text))

Max Activating Token Index: 756

Text #6

Max Range: 0.5853. Min Range: -0.5853

Max Act: 0.3220. Min Act: -0.0000

Data Index: 817943 (C4 (Web Text))

Max Activating Token Index: 779

Text #7

Max Range: 0.5853. Min Range: -0.5853

Max Act: 0.3458. Min Act: -0.0000

Data Index: 338473 (C4 (Web Text))

Max Activating Token Index: 646

Text #8

Max Range: 0.5853. Min Range: -0.5853

Max Act: 0.3051. Min Act: -0.0000

Data Index: 66969 (C4 (Web Text))

Max Activating Token Index: 705

Text #9

Max Range: 0.5853. Min Range: -0.5853

Max Act: 0.3057. Min Act: -0.0000

Data Index: 219019 (C4 (Web Text))

Max Activating Token Index: 436

Text #10

Max Range: 0.5853. Min Range: -0.5853

Max Act: 0.2865. Min Act: -0.0000

Data Index: 183429 (C4 (Web Text))

Max Activating Token Index: 325

Text #11

Max Range: 0.5853. Min Range: -0.5853

Max Act: 0.2727. Min Act: -0.0000

Data Index: 432115 (C4 (Web Text))

Max Activating Token Index: 561

Text #12

Max Range: 0.5853. Min Range: -0.5853

Max Act: 0.3010. Min Act: -0.0000

Data Index: 1074545 (C4 (Web Text))

Max Activating Token Index: 629

Text #13

Max Range: 0.5853. Min Range: -0.5853

Max Act: 0.2809. Min Act: -0.0000

Data Index: 208226 (C4 (Web Text))

Max Activating Token Index: 783

Text #14

Max Range: 0.5853. Min Range: -0.5853

Max Act: 0.2863. Min Act: -0.0000

Data Index: 948449 (C4 (Web Text))

Max Activating Token Index: 138

Text #15

Max Range: 0.5853. Min Range: -0.5853

Max Act: 0.2843. Min Act: -0.0000

Data Index: 394057 (C4 (Web Text))

Max Activating Token Index: 498

Text #16

Max Range: 0.5853. Min Range: -0.5853

Max Act: 0.2784. Min Act: -0.0000

Data Index: 517646 (C4 (Web Text))

Max Activating Token Index: 195

Text #17

Max Range: 0.5853. Min Range: -0.5853

Max Act: 0.2825. Min Act: -0.0000

Data Index: 819127 (C4 (Web Text))

Max Activating Token Index: 815

Text #18

Max Range: 0.5853. Min Range: -0.5853

Max Act: 0.2527. Min Act: -0.0000

Data Index: 1239897 (C4 (Web Text))

Max Activating Token Index: 585

Text #19

Max Range: 0.5853. Min Range: -0.5853

Max Act: 0.2711. Min Act: -0.0000

Data Index: 992962 (C4 (Web Text))

Max Activating Token Index: 311