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

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

Neuron 4729 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7062. Min Range: -2.7062

Max Act: 2.7062. Min Act: -0.0000

Data Index: 1070269 (C4 (Web Text))

Max Activating Token Index: 12

Text #1

Max Range: 2.7062. Min Range: -2.7062

Max Act: 2.6759. Min Act: -0.0000

Data Index: 1351451 (C4 (Web Text))

Max Activating Token Index: 11

Text #2

Max Range: 2.7062. Min Range: -2.7062

Max Act: 2.0645. Min Act: -0.0000

Data Index: 832419 (C4 (Web Text))

Max Activating Token Index: 198

Text #3

Max Range: 2.7062. Min Range: -2.7062

Max Act: 1.9755. Min Act: -0.0000

Data Index: 773770 (C4 (Web Text))

Max Activating Token Index: 462

Text #4

Max Range: 2.7062. Min Range: -2.7062

Max Act: 1.8637. Min Act: -0.0000

Data Index: 499228 (C4 (Web Text))

Max Activating Token Index: 375

Text #5

Max Range: 2.7062. Min Range: -2.7062

Max Act: 1.9322. Min Act: -0.0000

Data Index: 1261971 (C4 (Web Text))

Max Activating Token Index: 195

Text #6

Max Range: 2.7062. Min Range: -2.7062

Max Act: 1.9271. Min Act: -0.0000

Data Index: 1087208 (C4 (Web Text))

Max Activating Token Index: 14

Text #7

Max Range: 2.7062. Min Range: -2.7062

Max Act: 1.9002. Min Act: -0.0000

Data Index: 652171 (C4 (Web Text))

Max Activating Token Index: 257

Text #8

Max Range: 2.7062. Min Range: -2.7062

Max Act: 1.8693. Min Act: -0.0000

Data Index: 198060 (C4 (Web Text))

Max Activating Token Index: 282

Text #9

Max Range: 2.7062. Min Range: -2.7062

Max Act: 1.7602. Min Act: -0.0000

Data Index: 279080 (C4 (Web Text))

Max Activating Token Index: 627

Text #10

Max Range: 2.7062. Min Range: -2.7062

Max Act: 1.7547. Min Act: -0.0000

Data Index: 354600 (C4 (Web Text))

Max Activating Token Index: 656

Text #11

Max Range: 2.7062. Min Range: -2.7062

Max Act: 1.7446. Min Act: -0.0000

Data Index: 1084624 (C4 (Web Text))

Max Activating Token Index: 829

Text #12

Max Range: 2.7062. Min Range: -2.7062

Max Act: 1.8456. Min Act: -0.0000

Data Index: 1136959 (C4 (Web Text))

Max Activating Token Index: 411

Text #13

Max Range: 2.7062. Min Range: -2.7062

Max Act: 1.8467. Min Act: -0.0000

Data Index: 22997 (C4 (Web Text))

Max Activating Token Index: 669

Text #14

Max Range: 2.7062. Min Range: -2.7062

Max Act: 1.8280. Min Act: -0.0000

Data Index: 1475 (C4 (Web Text))

Max Activating Token Index: 122

Text #15

Max Range: 2.7062. Min Range: -2.7062

Max Act: 1.9368. Min Act: -0.0000

Data Index: 1052332 (C4 (Web Text))

Max Activating Token Index: 10

Text #16

Max Range: 2.7062. Min Range: -2.7062

Max Act: 1.6415. Min Act: -0.0000

Data Index: 193171 (C4 (Web Text))

Max Activating Token Index: 886

Text #17

Max Range: 2.7062. Min Range: -2.7062

Max Act: 1.7623. Min Act: -0.0000

Data Index: 482582 (C4 (Web Text))

Max Activating Token Index: 591

Text #18

Max Range: 2.7062. Min Range: -2.7062

Max Act: 1.6337. Min Act: -0.0000

Data Index: 1249113 (C4 (Web Text))

Max Activating Token Index: 708

Text #19

Max Range: 2.7062. Min Range: -2.7062

Max Act: 1.6495. Min Act: -0.0000

Data Index: 123112 (C4 (Web Text))

Max Activating Token Index: 848