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

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

Neuron 3460 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4853. Min Range: -1.4853

Max Act: 1.4853. Min Act: -0.0000

Data Index: 149906 (C4 (Web Text))

Max Activating Token Index: 337

Text #1

Max Range: 1.4853. Min Range: -1.4853

Max Act: 1.4300. Min Act: -0.0000

Data Index: 709019 (C4 (Web Text))

Max Activating Token Index: 336

Text #2

Max Range: 1.4853. Min Range: -1.4853

Max Act: 1.2789. Min Act: -0.0000

Data Index: 36121 (C4 (Web Text))

Max Activating Token Index: 590

Text #3

Max Range: 1.4853. Min Range: -1.4853

Max Act: 1.1076. Min Act: -0.0000

Data Index: 1236935 (C4 (Web Text))

Max Activating Token Index: 574

Text #4

Max Range: 1.4853. Min Range: -1.4853

Max Act: 1.1951. Min Act: -0.0000

Data Index: 39750 (C4 (Web Text))

Max Activating Token Index: 300

Text #5

Max Range: 1.4853. Min Range: -1.4853

Max Act: 1.1421. Min Act: -0.0000

Data Index: 1190489 (C4 (Web Text))

Max Activating Token Index: 815

Text #6

Max Range: 1.4853. Min Range: -1.4853

Max Act: 1.0759. Min Act: -0.0000

Data Index: 995537 (C4 (Web Text))

Max Activating Token Index: 281

Text #7

Max Range: 1.4853. Min Range: -1.4853

Max Act: 0.9972. Min Act: -0.0000

Data Index: 139161 (C4 (Web Text))

Max Activating Token Index: 286

Text #8

Max Range: 1.4853. Min Range: -1.4853

Max Act: 1.0642. Min Act: -0.0000

Data Index: 930567 (C4 (Web Text))

Max Activating Token Index: 604

Text #9

Max Range: 1.4853. Min Range: -1.4853

Max Act: 1.0237. Min Act: -0.0000

Data Index: 827639 (C4 (Web Text))

Max Activating Token Index: 49

Text #10

Max Range: 1.4853. Min Range: -1.4853

Max Act: 1.0158. Min Act: -0.0000

Data Index: 84748 (C4 (Web Text))

Max Activating Token Index: 733

Text #11

Max Range: 1.4853. Min Range: -1.4853

Max Act: 1.0119. Min Act: -0.0000

Data Index: 885156 (C4 (Web Text))

Max Activating Token Index: 724

Text #12

Max Range: 1.4853. Min Range: -1.4853

Max Act: 1.0143. Min Act: -0.0000

Data Index: 549661 (C4 (Web Text))

Max Activating Token Index: 844

Text #13

Max Range: 1.4853. Min Range: -1.4853

Max Act: 1.0059. Min Act: -0.0000

Data Index: 802116 (C4 (Web Text))

Max Activating Token Index: 661

Text #14

Max Range: 1.4853. Min Range: -1.4853

Max Act: 1.0059. Min Act: -0.0000

Data Index: 214021 (C4 (Web Text))

Max Activating Token Index: 744

Text #15

Max Range: 1.4853. Min Range: -1.4853

Max Act: 0.9646. Min Act: -0.0000

Data Index: 830780 (C4 (Web Text))

Max Activating Token Index: 488

Text #16

Max Range: 1.4853. Min Range: -1.4853

Max Act: 0.9358. Min Act: -0.0000

Data Index: 956235 (C4 (Web Text))

Max Activating Token Index: 423

Text #17

Max Range: 1.4853. Min Range: -1.4853

Max Act: 1.0526. Min Act: -0.0000

Data Index: 1132060 (C4 (Web Text))

Max Activating Token Index: 440

Text #18

Max Range: 1.4853. Min Range: -1.4853

Max Act: 0.9977. Min Act: -0.0000

Data Index: 1119835 (C4 (Web Text))

Max Activating Token Index: 1008

Text #19

Max Range: 1.4853. Min Range: -1.4853

Max Act: 0.9825. Min Act: -0.0000

Data Index: 463787 (C4 (Web Text))

Max Activating Token Index: 225