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

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

Neuron 3699 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3775. Min Range: -1.3775

Max Act: 1.3775. Min Act: -0.0001

Data Index: 312609 (C4 (Web Text))

Max Activating Token Index: 894

Text #1

Max Range: 1.3775. Min Range: -1.3775

Max Act: 0.8549. Min Act: -0.0001

Data Index: 992233 (C4 (Web Text))

Max Activating Token Index: 894

Text #2

Max Range: 1.3775. Min Range: -1.3775

Max Act: 0.7400. Min Act: -0.0001

Data Index: 663965 (C4 (Web Text))

Max Activating Token Index: 833

Text #3

Max Range: 1.3775. Min Range: -1.3775

Max Act: 0.7266. Min Act: -0.0001

Data Index: 114074 (C4 (Web Text))

Max Activating Token Index: 389

Text #4

Max Range: 1.3775. Min Range: -1.3775

Max Act: 0.7111. Min Act: -0.0001

Data Index: 533715 (C4 (Web Text))

Max Activating Token Index: 132

Text #5

Max Range: 1.3775. Min Range: -1.3775

Max Act: 0.6352. Min Act: -0.0001

Data Index: 1111678 (C4 (Web Text))

Max Activating Token Index: 339

Text #6

Max Range: 1.3775. Min Range: -1.3775

Max Act: 0.6850. Min Act: -0.0001

Data Index: 653656 (C4 (Web Text))

Max Activating Token Index: 403

Text #7

Max Range: 1.3775. Min Range: -1.3775

Max Act: 0.6014. Min Act: -0.0001

Data Index: 1206196 (C4 (Web Text))

Max Activating Token Index: 986

Text #8

Max Range: 1.3775. Min Range: -1.3775

Max Act: 0.5970. Min Act: -0.0001

Data Index: 150343 (C4 (Web Text))

Max Activating Token Index: 915

Text #9

Max Range: 1.3775. Min Range: -1.3775

Max Act: 0.6140. Min Act: -0.0001

Data Index: 108836 (C4 (Web Text))

Max Activating Token Index: 10

Text #10

Max Range: 1.3775. Min Range: -1.3775

Max Act: 0.6518. Min Act: -0.0001

Data Index: 916536 (C4 (Web Text))

Max Activating Token Index: 788

Text #11

Max Range: 1.3775. Min Range: -1.3775

Max Act: 0.7071. Min Act: -0.0001

Data Index: 857083 (C4 (Web Text))

Max Activating Token Index: 436

Text #12

Max Range: 1.3775. Min Range: -1.3775

Max Act: 0.6868. Min Act: -0.0001

Data Index: 725169 (C4 (Web Text))

Max Activating Token Index: 145

Text #13

Max Range: 1.3775. Min Range: -1.3775

Max Act: 0.6038. Min Act: -0.0001

Data Index: 818257 (C4 (Web Text))

Max Activating Token Index: 649

Text #14

Max Range: 1.3775. Min Range: -1.3775

Max Act: 0.6631. Min Act: -0.0001

Data Index: 373658 (C4 (Web Text))

Max Activating Token Index: 791

Text #15

Max Range: 1.3775. Min Range: -1.3775

Max Act: 0.7472. Min Act: -0.0001

Data Index: 187668 (C4 (Web Text))

Max Activating Token Index: 253

Text #16

Max Range: 1.3775. Min Range: -1.3775

Max Act: 0.5866. Min Act: -0.0001

Data Index: 1081452 (C4 (Web Text))

Max Activating Token Index: 749

Text #17

Max Range: 1.3775. Min Range: -1.3775

Max Act: 0.5305. Min Act: -0.0001

Data Index: 922717 (C4 (Web Text))

Max Activating Token Index: 312

Text #18

Max Range: 1.3775. Min Range: -1.3775

Max Act: 0.5241. Min Act: -0.0001

Data Index: 646558 (C4 (Web Text))

Max Activating Token Index: 681

Text #19

Max Range: 1.3775. Min Range: -1.3775

Max Act: 0.6241. Min Act: -0.0001

Data Index: 849116 (C4 (Web Text))

Max Activating Token Index: 738