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

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

Neuron 150 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1033. Min Range: -0.1033

Max Act: 0.1033. Min Act: -0.0002

Data Index: 124212 (C4 (Web Text))

Max Activating Token Index: 208

Text #1

Max Range: 0.1033. Min Range: -0.1033

Max Act: 0.1031. Min Act: -0.0002

Data Index: 349705 (C4 (Web Text))

Max Activating Token Index: 70

Text #2

Max Range: 0.1033. Min Range: -0.1033

Max Act: 0.0874. Min Act: -0.0002

Data Index: 168536 (C4 (Web Text))

Max Activating Token Index: 394

Text #3

Max Range: 0.1033. Min Range: -0.1033

Max Act: 0.0939. Min Act: -0.0002

Data Index: 605824 (C4 (Web Text))

Max Activating Token Index: 785

Text #4

Max Range: 0.1033. Min Range: -0.1033

Max Act: 0.0815. Min Act: -0.0002

Data Index: 863707 (C4 (Web Text))

Max Activating Token Index: 459

Text #5

Max Range: 0.1033. Min Range: -0.1033

Max Act: 0.0842. Min Act: -0.0002

Data Index: 120837 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.1033. Min Range: -0.1033

Max Act: 0.0810. Min Act: -0.0002

Data Index: 5310 (C4 (Web Text))

Max Activating Token Index: 229

Text #7

Max Range: 0.1033. Min Range: -0.1033

Max Act: 0.0743. Min Act: -0.0002

Data Index: 621099 (C4 (Web Text))

Max Activating Token Index: 654

Text #8

Max Range: 0.1033. Min Range: -0.1033

Max Act: 0.0744. Min Act: -0.0002

Data Index: 136451 (C4 (Web Text))

Max Activating Token Index: 84

Text #9

Max Range: 0.1033. Min Range: -0.1033

Max Act: 0.0877. Min Act: -0.0002

Data Index: 524935 (C4 (Web Text))

Max Activating Token Index: 781

Text #10

Max Range: 0.1033. Min Range: -0.1033

Max Act: 0.0778. Min Act: -0.0002

Data Index: 1323817 (C4 (Web Text))

Max Activating Token Index: 233

Text #11

Max Range: 0.1033. Min Range: -0.1033

Max Act: 0.0755. Min Act: -0.0002

Data Index: 393299 (C4 (Web Text))

Max Activating Token Index: 61

Text #12

Max Range: 0.1033. Min Range: -0.1033

Max Act: 0.0730. Min Act: -0.0002

Data Index: 404306 (C4 (Web Text))

Max Activating Token Index: 517

Text #13

Max Range: 0.1033. Min Range: -0.1033

Max Act: 0.0716. Min Act: -0.0002

Data Index: 626089 (C4 (Web Text))

Max Activating Token Index: 810

Text #14

Max Range: 0.1033. Min Range: -0.1033

Max Act: 0.0801. Min Act: -0.0002

Data Index: 1076567 (C4 (Web Text))

Max Activating Token Index: 276

Text #15

Max Range: 0.1033. Min Range: -0.1033

Max Act: 0.0737. Min Act: -0.0002

Data Index: 108385 (C4 (Web Text))

Max Activating Token Index: 406

Text #16

Max Range: 0.1033. Min Range: -0.1033

Max Act: 0.0756. Min Act: -0.0002

Data Index: 429893 (C4 (Web Text))

Max Activating Token Index: 443

Text #17

Max Range: 0.1033. Min Range: -0.1033

Max Act: 0.0810. Min Act: -0.0002

Data Index: 774151 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.1033. Min Range: -0.1033

Max Act: 0.0696. Min Act: -0.0002

Data Index: 866964 (C4 (Web Text))

Max Activating Token Index: 838

Text #19

Max Range: 0.1033. Min Range: -0.1033

Max Act: 0.0828. Min Act: -0.0002

Data Index: 1224911 (C4 (Web Text))

Max Activating Token Index: 169