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

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

Neuron 5438 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2363. Min Range: -2.2363

Max Act: 2.2363. Min Act: -0.0000

Data Index: 405186 (C4 (Web Text))

Max Activating Token Index: 632

Text #1

Max Range: 2.2363. Min Range: -2.2363

Max Act: 2.1068. Min Act: -0.0000

Data Index: 1281127 (C4 (Web Text))

Max Activating Token Index: 922

Text #2

Max Range: 2.2363. Min Range: -2.2363

Max Act: 1.8507. Min Act: -0.0001

Data Index: 782622 (C4 (Web Text))

Max Activating Token Index: 22

Text #3

Max Range: 2.2363. Min Range: -2.2363

Max Act: 1.8020. Min Act: -0.0000

Data Index: 522298 (C4 (Web Text))

Max Activating Token Index: 185

Text #4

Max Range: 2.2363. Min Range: -2.2363

Max Act: 1.6943. Min Act: -0.0000

Data Index: 227600 (C4 (Web Text))

Max Activating Token Index: 74

Text #5

Max Range: 2.2363. Min Range: -2.2363

Max Act: 1.4760. Min Act: -0.0000

Data Index: 458664 (C4 (Web Text))

Max Activating Token Index: 332

Text #6

Max Range: 2.2363. Min Range: -2.2363

Max Act: 1.3355. Min Act: -0.0000

Data Index: 349079 (C4 (Web Text))

Max Activating Token Index: 410

Text #7

Max Range: 2.2363. Min Range: -2.2363

Max Act: 1.3217. Min Act: -0.0000

Data Index: 1346329 (C4 (Web Text))

Max Activating Token Index: 330

Text #8

Max Range: 2.2363. Min Range: -2.2363

Max Act: 1.3976. Min Act: -0.0000

Data Index: 1279703 (C4 (Web Text))

Max Activating Token Index: 142

Text #9

Max Range: 2.2363. Min Range: -2.2363

Max Act: 1.3639. Min Act: -0.0001

Data Index: 304784 (C4 (Web Text))

Max Activating Token Index: 162

Text #10

Max Range: 2.2363. Min Range: -2.2363

Max Act: 1.3089. Min Act: -0.0001

Data Index: 1186886 (C4 (Web Text))

Max Activating Token Index: 557

Text #11

Max Range: 2.2363. Min Range: -2.2363

Max Act: 1.2901. Min Act: -0.0000

Data Index: 1165770 (C4 (Web Text))

Max Activating Token Index: 956

Text #12

Max Range: 2.2363. Min Range: -2.2363

Max Act: 1.2610. Min Act: -0.0001

Data Index: 321553 (C4 (Web Text))

Max Activating Token Index: 57

Text #13

Max Range: 2.2363. Min Range: -2.2363

Max Act: 1.4132. Min Act: -0.0000

Data Index: 890843 (C4 (Web Text))

Max Activating Token Index: 770

Text #14

Max Range: 2.2363. Min Range: -2.2363

Max Act: 1.1475. Min Act: -0.0000

Data Index: 403720 (C4 (Web Text))

Max Activating Token Index: 162

Text #15

Max Range: 2.2363. Min Range: -2.2363

Max Act: 1.2145. Min Act: -0.0001

Data Index: 271057 (C4 (Web Text))

Max Activating Token Index: 245

Text #16

Max Range: 2.2363. Min Range: -2.2363

Max Act: 1.2817. Min Act: -0.0000

Data Index: 751491 (C4 (Web Text))

Max Activating Token Index: 837

Text #17

Max Range: 2.2363. Min Range: -2.2363

Max Act: 1.1826. Min Act: -0.0000

Data Index: 236485 (C4 (Web Text))

Max Activating Token Index: 725

Text #18

Max Range: 2.2363. Min Range: -2.2363

Max Act: 1.1518. Min Act: -0.0000

Data Index: 982908 (C4 (Web Text))

Max Activating Token Index: 696

Text #19

Max Range: 2.2363. Min Range: -2.2363

Max Act: 1.1795. Min Act: -0.0000

Data Index: 358346 (C4 (Web Text))

Max Activating Token Index: 648