Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1504 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1254. Min Range: -0.1254

Max Act: 0.1254. Min Act: -0.0003

Data Index: 596364 (C4 (Web Text))

Max Activating Token Index: 834

Text #1

Max Range: 0.1254. Min Range: -0.1254

Max Act: 0.1059. Min Act: -0.0003

Data Index: 236998 (C4 (Web Text))

Max Activating Token Index: 280

Text #2

Max Range: 0.1254. Min Range: -0.1254

Max Act: 0.1020. Min Act: -0.0003

Data Index: 1154942 (C4 (Web Text))

Max Activating Token Index: 223

Text #3

Max Range: 0.1254. Min Range: -0.1254

Max Act: 0.0781. Min Act: -0.0003

Data Index: 1340303 (C4 (Web Text))

Max Activating Token Index: 198

Text #4

Max Range: 0.1254. Min Range: -0.1254

Max Act: 0.0732. Min Act: -0.0003

Data Index: 1200673 (C4 (Web Text))

Max Activating Token Index: 277

Text #5

Max Range: 0.1254. Min Range: -0.1254

Max Act: 0.0725. Min Act: -0.0003

Data Index: 1312369 (C4 (Web Text))

Max Activating Token Index: 98

Text #6

Max Range: 0.1254. Min Range: -0.1254

Max Act: 0.0776. Min Act: -0.0003

Data Index: 980825 (C4 (Web Text))

Max Activating Token Index: 442

Text #7

Max Range: 0.1254. Min Range: -0.1254

Max Act: 0.0741. Min Act: -0.0003

Data Index: 351229 (C4 (Web Text))

Max Activating Token Index: 695

Text #8

Max Range: 0.1254. Min Range: -0.1254

Max Act: 0.0718. Min Act: -0.0003

Data Index: 1357749 (C4 (Web Text))

Max Activating Token Index: 336

Text #9

Max Range: 0.1254. Min Range: -0.1254

Max Act: 0.0666. Min Act: -0.0003

Data Index: 892588 (C4 (Web Text))

Max Activating Token Index: 167

Text #10

Max Range: 0.1254. Min Range: -0.1254

Max Act: 0.0698. Min Act: -0.0003

Data Index: 86875 (C4 (Web Text))

Max Activating Token Index: 27

Text #11

Max Range: 0.1254. Min Range: -0.1254

Max Act: 0.0716. Min Act: -0.0003

Data Index: 520431 (C4 (Web Text))

Max Activating Token Index: 47

Text #12

Max Range: 0.1254. Min Range: -0.1254

Max Act: 0.0672. Min Act: -0.0003

Data Index: 768498 (C4 (Web Text))

Max Activating Token Index: 270

Text #13

Max Range: 0.1254. Min Range: -0.1254

Max Act: 0.0653. Min Act: -0.0003

Data Index: 706204 (C4 (Web Text))

Max Activating Token Index: 188

Text #14

Max Range: 0.1254. Min Range: -0.1254

Max Act: 0.0675. Min Act: -0.0003

Data Index: 165467 (C4 (Web Text))

Max Activating Token Index: 37

Text #15

Max Range: 0.1254. Min Range: -0.1254

Max Act: 0.0666. Min Act: -0.0003

Data Index: 941783 (C4 (Web Text))

Max Activating Token Index: 12

Text #16

Max Range: 0.1254. Min Range: -0.1254

Max Act: 0.0669. Min Act: -0.0003

Data Index: 620408 (C4 (Web Text))

Max Activating Token Index: 516

Text #17

Max Range: 0.1254. Min Range: -0.1254

Max Act: 0.0680. Min Act: -0.0003

Data Index: 1114601 (C4 (Web Text))

Max Activating Token Index: 42

Text #18

Max Range: 0.1254. Min Range: -0.1254

Max Act: 0.0656. Min Act: -0.0003

Data Index: 1285128 (C4 (Web Text))

Max Activating Token Index: 14

Text #19

Max Range: 0.1254. Min Range: -0.1254

Max Act: 0.0677. Min Act: -0.0003

Data Index: 1276753 (C4 (Web Text))

Max Activating Token Index: 138