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

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

Neuron 3449 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3877. Min Range: -3.3877

Max Act: 3.3877. Min Act: -0.0000

Data Index: 71124 (C4 (Web Text))

Max Activating Token Index: 478

Text #1

Max Range: 3.3877. Min Range: -3.3877

Max Act: 3.0715. Min Act: -0.0000

Data Index: 21785 (C4 (Web Text))

Max Activating Token Index: 584

Text #2

Max Range: 3.3877. Min Range: -3.3877

Max Act: 2.7716. Min Act: -0.0000

Data Index: 1010392 (C4 (Web Text))

Max Activating Token Index: 245

Text #3

Max Range: 3.3877. Min Range: -3.3877

Max Act: 2.5668. Min Act: -0.0000

Data Index: 156419 (C4 (Web Text))

Max Activating Token Index: 822

Text #4

Max Range: 3.3877. Min Range: -3.3877

Max Act: 2.0496. Min Act: -0.0000

Data Index: 274125 (C4 (Web Text))

Max Activating Token Index: 580

Text #5

Max Range: 3.3877. Min Range: -3.3877

Max Act: 1.7645. Min Act: -0.0000

Data Index: 507980 (C4 (Web Text))

Max Activating Token Index: 514

Text #6

Max Range: 3.3877. Min Range: -3.3877

Max Act: 1.8299. Min Act: -0.0000

Data Index: 506883 (C4 (Web Text))

Max Activating Token Index: 21

Text #7

Max Range: 3.3877. Min Range: -3.3877

Max Act: 1.6709. Min Act: -0.0000

Data Index: 1023705 (C4 (Web Text))

Max Activating Token Index: 345

Text #8

Max Range: 3.3877. Min Range: -3.3877

Max Act: 1.8646. Min Act: -0.0000

Data Index: 822216 (C4 (Web Text))

Max Activating Token Index: 436

Text #9

Max Range: 3.3877. Min Range: -3.3877

Max Act: 1.7500. Min Act: -0.0000

Data Index: 1281680 (C4 (Web Text))

Max Activating Token Index: 177

Text #10

Max Range: 3.3877. Min Range: -3.3877

Max Act: 1.8181. Min Act: -0.0000

Data Index: 1111839 (C4 (Web Text))

Max Activating Token Index: 307

Text #11

Max Range: 3.3877. Min Range: -3.3877

Max Act: 1.7064. Min Act: -0.0000

Data Index: 217043 (C4 (Web Text))

Max Activating Token Index: 643

Text #12

Max Range: 3.3877. Min Range: -3.3877

Max Act: 1.5135. Min Act: -0.0000

Data Index: 772606 (C4 (Web Text))

Max Activating Token Index: 795

Text #13

Max Range: 3.3877. Min Range: -3.3877

Max Act: 1.7706. Min Act: -0.0000

Data Index: 331721 (C4 (Web Text))

Max Activating Token Index: 145

Text #14

Max Range: 3.3877. Min Range: -3.3877

Max Act: 1.6852. Min Act: -0.0000

Data Index: 34342 (C4 (Web Text))

Max Activating Token Index: 1021

Text #15

Max Range: 3.3877. Min Range: -3.3877

Max Act: 1.6806. Min Act: -0.0000

Data Index: 1298994 (C4 (Web Text))

Max Activating Token Index: 550

Text #16

Max Range: 3.3877. Min Range: -3.3877

Max Act: 1.6604. Min Act: -0.0000

Data Index: 503584 (C4 (Web Text))

Max Activating Token Index: 731

Text #17

Max Range: 3.3877. Min Range: -3.3877

Max Act: 1.6691. Min Act: -0.0000

Data Index: 546596 (C4 (Web Text))

Max Activating Token Index: 721

Text #18

Max Range: 3.3877. Min Range: -3.3877

Max Act: 1.5558. Min Act: -0.0000

Data Index: 1319976 (C4 (Web Text))

Max Activating Token Index: 445

Text #19

Max Range: 3.3877. Min Range: -3.3877

Max Act: 1.5909. Min Act: -0.0000

Data Index: 368025 (C4 (Web Text))

Max Activating Token Index: 108