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

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

Neuron 4223 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5759. Min Range: -1.5759

Max Act: 1.5759. Min Act: -0.0001

Data Index: 952681 (C4 (Web Text))

Max Activating Token Index: 443

Text #1

Max Range: 1.5759. Min Range: -1.5759

Max Act: 1.4062. Min Act: -0.0001

Data Index: 1001769 (C4 (Web Text))

Max Activating Token Index: 970

Text #2

Max Range: 1.5759. Min Range: -1.5759

Max Act: 1.5749. Min Act: -0.0001

Data Index: 1012042 (C4 (Web Text))

Max Activating Token Index: 608

Text #3

Max Range: 1.5759. Min Range: -1.5759

Max Act: 1.5730. Min Act: -0.0001

Data Index: 1234979 (C4 (Web Text))

Max Activating Token Index: 545

Text #4

Max Range: 1.5759. Min Range: -1.5759

Max Act: 1.4747. Min Act: -0.0001

Data Index: 1177486 (C4 (Web Text))

Max Activating Token Index: 604

Text #5

Max Range: 1.5759. Min Range: -1.5759

Max Act: 1.5594. Min Act: -0.0001

Data Index: 439524 (C4 (Web Text))

Max Activating Token Index: 595

Text #6

Max Range: 1.5759. Min Range: -1.5759

Max Act: 1.4320. Min Act: -0.0001

Data Index: 1249728 (C4 (Web Text))

Max Activating Token Index: 169

Text #7

Max Range: 1.5759. Min Range: -1.5759

Max Act: 1.4989. Min Act: -0.0001

Data Index: 305765 (C4 (Web Text))

Max Activating Token Index: 497

Text #8

Max Range: 1.5759. Min Range: -1.5759

Max Act: 1.4937. Min Act: -0.0001

Data Index: 783143 (C4 (Web Text))

Max Activating Token Index: 1007

Text #9

Max Range: 1.5759. Min Range: -1.5759

Max Act: 1.4962. Min Act: -0.0001

Data Index: 1349396 (C4 (Web Text))

Max Activating Token Index: 836

Text #10

Max Range: 1.5759. Min Range: -1.5759

Max Act: 1.4448. Min Act: -0.0001

Data Index: 767970 (C4 (Web Text))

Max Activating Token Index: 24

Text #11

Max Range: 1.5759. Min Range: -1.5759

Max Act: 1.4188. Min Act: -0.0001

Data Index: 976249 (C4 (Web Text))

Max Activating Token Index: 683

Text #12

Max Range: 1.5759. Min Range: -1.5759

Max Act: 1.4074. Min Act: -0.0001

Data Index: 901736 (C4 (Web Text))

Max Activating Token Index: 973

Text #13

Max Range: 1.5759. Min Range: -1.5759

Max Act: 1.3215. Min Act: -0.0001

Data Index: 533001 (C4 (Web Text))

Max Activating Token Index: 689

Text #14

Max Range: 1.5759. Min Range: -1.5759

Max Act: 1.3286. Min Act: -0.0001

Data Index: 312284 (C4 (Web Text))

Max Activating Token Index: 9

Text #15

Max Range: 1.5759. Min Range: -1.5759

Max Act: 1.4019. Min Act: -0.0001

Data Index: 1195790 (C4 (Web Text))

Max Activating Token Index: 33

Text #16

Max Range: 1.5759. Min Range: -1.5759

Max Act: 1.3932. Min Act: -0.0001

Data Index: 646301 (C4 (Web Text))

Max Activating Token Index: 965

Text #17

Max Range: 1.5759. Min Range: -1.5759

Max Act: 1.3929. Min Act: -0.0001

Data Index: 932305 (C4 (Web Text))

Max Activating Token Index: 1017

Text #18

Max Range: 1.5759. Min Range: -1.5759

Max Act: 1.2338. Min Act: -0.0001

Data Index: 557656 (C4 (Web Text))

Max Activating Token Index: 89

Text #19

Max Range: 1.5759. Min Range: -1.5759

Max Act: 1.3835. Min Act: -0.0001

Data Index: 536324 (C4 (Web Text))

Max Activating Token Index: 998