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

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

Neuron 13 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: 1.6632. Min Range: -1.6632

Max Act: 1.6632. Min Act: -0.0000

Data Index: 471984 (C4 (Web Text))

Max Activating Token Index: 386

Text #1

Max Range: 1.6632. Min Range: -1.6632

Max Act: 0.8672. Min Act: -0.0000

Data Index: 1006160 (C4 (Web Text))

Max Activating Token Index: 1018

Text #2

Max Range: 1.6632. Min Range: -1.6632

Max Act: 0.7368. Min Act: -0.0000

Data Index: 157374 (C4 (Web Text))

Max Activating Token Index: 976

Text #3

Max Range: 1.6632. Min Range: -1.6632

Max Act: 0.7237. Min Act: -0.0000

Data Index: 742553 (C4 (Web Text))

Max Activating Token Index: 122

Text #4

Max Range: 1.6632. Min Range: -1.6632

Max Act: 0.7001. Min Act: -0.0000

Data Index: 6855 (C4 (Web Text))

Max Activating Token Index: 316

Text #5

Max Range: 1.6632. Min Range: -1.6632

Max Act: 0.7345. Min Act: -0.0000

Data Index: 955684 (C4 (Web Text))

Max Activating Token Index: 93

Text #6

Max Range: 1.6632. Min Range: -1.6632

Max Act: 0.5788. Min Act: -0.0000

Data Index: 267508 (C4 (Web Text))

Max Activating Token Index: 577

Text #7

Max Range: 1.6632. Min Range: -1.6632

Max Act: 0.6096. Min Act: -0.0000

Data Index: 1043877 (C4 (Web Text))

Max Activating Token Index: 564

Text #8

Max Range: 1.6632. Min Range: -1.6632

Max Act: 0.6010. Min Act: -0.0000

Data Index: 1317922 (C4 (Web Text))

Max Activating Token Index: 153

Text #9

Max Range: 1.6632. Min Range: -1.6632

Max Act: 0.6005. Min Act: -0.0000

Data Index: 815580 (C4 (Web Text))

Max Activating Token Index: 204

Text #10

Max Range: 1.6632. Min Range: -1.6632

Max Act: 0.6053. Min Act: -0.0000

Data Index: 1012368 (C4 (Web Text))

Max Activating Token Index: 1017

Text #11

Max Range: 1.6632. Min Range: -1.6632

Max Act: 0.6038. Min Act: -0.0000

Data Index: 560970 (C4 (Web Text))

Max Activating Token Index: 295

Text #12

Max Range: 1.6632. Min Range: -1.6632

Max Act: 0.5989. Min Act: -0.0000

Data Index: 579787 (C4 (Web Text))

Max Activating Token Index: 102

Text #13

Max Range: 1.6632. Min Range: -1.6632

Max Act: 0.6637. Min Act: -0.0000

Data Index: 426947 (C4 (Web Text))

Max Activating Token Index: 190

Text #14

Max Range: 1.6632. Min Range: -1.6632

Max Act: 0.5124. Min Act: -0.0000

Data Index: 1159908 (C4 (Web Text))

Max Activating Token Index: 572

Text #15

Max Range: 1.6632. Min Range: -1.6632

Max Act: 0.6042. Min Act: -0.0000

Data Index: 538960 (C4 (Web Text))

Max Activating Token Index: 898

Text #16

Max Range: 1.6632. Min Range: -1.6632

Max Act: 0.4613. Min Act: -0.0000

Data Index: 155007 (C4 (Web Text))

Max Activating Token Index: 565

Text #17

Max Range: 1.6632. Min Range: -1.6632

Max Act: 0.5218. Min Act: -0.0000

Data Index: 248507 (C4 (Web Text))

Max Activating Token Index: 732

Text #18

Max Range: 1.6632. Min Range: -1.6632

Max Act: 0.5410. Min Act: -0.0000

Data Index: 1647828 (Python Code)

Max Activating Token Index: 120

Text #19

Max Range: 1.6632. Min Range: -1.6632

Max Act: 0.5032. Min Act: -0.0000

Data Index: 1424540 (Python Code)

Max Activating Token Index: 361