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

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

Neuron 4238 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: 0.1312. Min Range: -0.1312

Max Act: 0.1312. Min Act: -0.0002

Data Index: 421505 (C4 (Web Text))

Max Activating Token Index: 947

Text #1

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.1275. Min Act: -0.0002

Data Index: 419717 (C4 (Web Text))

Max Activating Token Index: 199

Text #2

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.0988. Min Act: -0.0002

Data Index: 40342 (C4 (Web Text))

Max Activating Token Index: 492

Text #3

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.0993. Min Act: -0.0002

Data Index: 527199 (C4 (Web Text))

Max Activating Token Index: 260

Text #4

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.0993. Min Act: -0.0002

Data Index: 547829 (C4 (Web Text))

Max Activating Token Index: 337

Text #5

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.0890. Min Act: -0.0002

Data Index: 1141674 (C4 (Web Text))

Max Activating Token Index: 668

Text #6

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.0959. Min Act: -0.0002

Data Index: 576809 (C4 (Web Text))

Max Activating Token Index: 418

Text #7

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.0973. Min Act: -0.0002

Data Index: 764310 (C4 (Web Text))

Max Activating Token Index: 377

Text #8

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.0929. Min Act: -0.0002

Data Index: 1309437 (C4 (Web Text))

Max Activating Token Index: 1021

Text #9

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.0952. Min Act: -0.0002

Data Index: 320889 (C4 (Web Text))

Max Activating Token Index: 258

Text #10

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.0900. Min Act: -0.0002

Data Index: 889146 (C4 (Web Text))

Max Activating Token Index: 965

Text #11

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.0876. Min Act: -0.0002

Data Index: 523575 (C4 (Web Text))

Max Activating Token Index: 1008

Text #12

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.0828. Min Act: -0.0002

Data Index: 1243043 (C4 (Web Text))

Max Activating Token Index: 714

Text #13

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.0765. Min Act: -0.0002

Data Index: 907527 (C4 (Web Text))

Max Activating Token Index: 440

Text #14

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.0785. Min Act: -0.0002

Data Index: 1273744 (C4 (Web Text))

Max Activating Token Index: 238

Text #15

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.0752. Min Act: -0.0002

Data Index: 1352507 (C4 (Web Text))

Max Activating Token Index: 498

Text #16

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.0833. Min Act: -0.0002

Data Index: 28972 (C4 (Web Text))

Max Activating Token Index: 118

Text #17

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.0809. Min Act: -0.0002

Data Index: 480196 (C4 (Web Text))

Max Activating Token Index: 660

Text #18

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.0712. Min Act: -0.0002

Data Index: 968414 (C4 (Web Text))

Max Activating Token Index: 545

Text #19

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.0715. Min Act: -0.0002

Data Index: 664038 (C4 (Web Text))

Max Activating Token Index: 584