Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3150 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.9079. Min Range: -0.9079

Max Act: 0.9079. Min Act: -0.0000

Data Index: 299265 (C4 (Web Text))

Max Activating Token Index: 509

Text #1

Max Range: 0.9079. Min Range: -0.9079

Max Act: 0.8064. Min Act: -0.0000

Data Index: 323814 (C4 (Web Text))

Max Activating Token Index: 273

Text #2

Max Range: 0.9079. Min Range: -0.9079

Max Act: 0.7923. Min Act: -0.0000

Data Index: 160365 (C4 (Web Text))

Max Activating Token Index: 672

Text #3

Max Range: 0.9079. Min Range: -0.9079

Max Act: 0.7706. Min Act: -0.0000

Data Index: 612275 (C4 (Web Text))

Max Activating Token Index: 843

Text #4

Max Range: 0.9079. Min Range: -0.9079

Max Act: 0.7818. Min Act: -0.0000

Data Index: 1321421 (C4 (Web Text))

Max Activating Token Index: 484

Text #5

Max Range: 0.9079. Min Range: -0.9079

Max Act: 0.7631. Min Act: -0.0000

Data Index: 344600 (C4 (Web Text))

Max Activating Token Index: 86

Text #6

Max Range: 0.9079. Min Range: -0.9079

Max Act: 0.7161. Min Act: -0.0000

Data Index: 450467 (C4 (Web Text))

Max Activating Token Index: 812

Text #7

Max Range: 0.9079. Min Range: -0.9079

Max Act: 0.7513. Min Act: -0.0000

Data Index: 1112208 (C4 (Web Text))

Max Activating Token Index: 178

Text #8

Max Range: 0.9079. Min Range: -0.9079

Max Act: 0.7046. Min Act: -0.0000

Data Index: 63482 (C4 (Web Text))

Max Activating Token Index: 970

Text #9

Max Range: 0.9079. Min Range: -0.9079

Max Act: 0.6586. Min Act: -0.0000

Data Index: 1304379 (C4 (Web Text))

Max Activating Token Index: 734

Text #10

Max Range: 0.9079. Min Range: -0.9079

Max Act: 0.7444. Min Act: -0.0000

Data Index: 98877 (C4 (Web Text))

Max Activating Token Index: 641

Text #11

Max Range: 0.9079. Min Range: -0.9079

Max Act: 0.6474. Min Act: -0.0000

Data Index: 708294 (C4 (Web Text))

Max Activating Token Index: 130

Text #12

Max Range: 0.9079. Min Range: -0.9079

Max Act: 0.6593. Min Act: -0.0000

Data Index: 906967 (C4 (Web Text))

Max Activating Token Index: 521

Text #13

Max Range: 0.9079. Min Range: -0.9079

Max Act: 0.6617. Min Act: -0.0000

Data Index: 504549 (C4 (Web Text))

Max Activating Token Index: 654

Text #14

Max Range: 0.9079. Min Range: -0.9079

Max Act: 0.6497. Min Act: -0.0000

Data Index: 63893 (C4 (Web Text))

Max Activating Token Index: 271

Text #15

Max Range: 0.9079. Min Range: -0.9079

Max Act: 0.6075. Min Act: -0.0000

Data Index: 898934 (C4 (Web Text))

Max Activating Token Index: 29

Text #16

Max Range: 0.9079. Min Range: -0.9079

Max Act: 0.6609. Min Act: -0.0000

Data Index: 1205273 (C4 (Web Text))

Max Activating Token Index: 47

Text #17

Max Range: 0.9079. Min Range: -0.9079

Max Act: 0.6398. Min Act: -0.0000

Data Index: 791069 (C4 (Web Text))

Max Activating Token Index: 688

Text #18

Max Range: 0.9079. Min Range: -0.9079

Max Act: 0.6539. Min Act: -0.0000

Data Index: 371555 (C4 (Web Text))

Max Activating Token Index: 968

Text #19

Max Range: 0.9079. Min Range: -0.9079

Max Act: 0.6236. Min Act: -0.0000

Data Index: 1004737 (C4 (Web Text))

Max Activating Token Index: 334