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

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

Neuron 3102 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: 1.5562. Min Range: -1.5562

Max Act: 1.5562. Min Act: -0.0000

Data Index: 1177567 (C4 (Web Text))

Max Activating Token Index: 35

Text #1

Max Range: 1.5562. Min Range: -1.5562

Max Act: 1.3462. Min Act: -0.0000

Data Index: 920272 (C4 (Web Text))

Max Activating Token Index: 524

Text #2

Max Range: 1.5562. Min Range: -1.5562

Max Act: 1.3430. Min Act: -0.0000

Data Index: 1139120 (C4 (Web Text))

Max Activating Token Index: 745

Text #3

Max Range: 1.5562. Min Range: -1.5562

Max Act: 1.1466. Min Act: -0.0000

Data Index: 530283 (C4 (Web Text))

Max Activating Token Index: 684

Text #4

Max Range: 1.5562. Min Range: -1.5562

Max Act: 1.2073. Min Act: -0.0000

Data Index: 251128 (C4 (Web Text))

Max Activating Token Index: 122

Text #5

Max Range: 1.5562. Min Range: -1.5562

Max Act: 1.1889. Min Act: -0.0000

Data Index: 1356368 (C4 (Web Text))

Max Activating Token Index: 6

Text #6

Max Range: 1.5562. Min Range: -1.5562

Max Act: 1.1821. Min Act: -0.0000

Data Index: 1070392 (C4 (Web Text))

Max Activating Token Index: 662

Text #7

Max Range: 1.5562. Min Range: -1.5562

Max Act: 1.1383. Min Act: -0.0000

Data Index: 269684 (C4 (Web Text))

Max Activating Token Index: 749

Text #8

Max Range: 1.5562. Min Range: -1.5562

Max Act: 1.2079. Min Act: -0.0000

Data Index: 820305 (C4 (Web Text))

Max Activating Token Index: 697

Text #9

Max Range: 1.5562. Min Range: -1.5562

Max Act: 1.1139. Min Act: -0.0000

Data Index: 688834 (C4 (Web Text))

Max Activating Token Index: 778

Text #10

Max Range: 1.5562. Min Range: -1.5562

Max Act: 0.9190. Min Act: -0.0000

Data Index: 832838 (C4 (Web Text))

Max Activating Token Index: 307

Text #11

Max Range: 1.5562. Min Range: -1.5562

Max Act: 1.0255. Min Act: -0.0000

Data Index: 999931 (C4 (Web Text))

Max Activating Token Index: 264

Text #12

Max Range: 1.5562. Min Range: -1.5562

Max Act: 1.1288. Min Act: -0.0000

Data Index: 820244 (C4 (Web Text))

Max Activating Token Index: 792

Text #13

Max Range: 1.5562. Min Range: -1.5562

Max Act: 1.1591. Min Act: -0.0000

Data Index: 634490 (C4 (Web Text))

Max Activating Token Index: 285

Text #14

Max Range: 1.5562. Min Range: -1.5562

Max Act: 1.0950. Min Act: -0.0000

Data Index: 736225 (C4 (Web Text))

Max Activating Token Index: 788

Text #15

Max Range: 1.5562. Min Range: -1.5562

Max Act: 1.1357. Min Act: -0.0000

Data Index: 1319886 (C4 (Web Text))

Max Activating Token Index: 33

Text #16

Max Range: 1.5562. Min Range: -1.5562

Max Act: 1.0821. Min Act: -0.0000

Data Index: 855282 (C4 (Web Text))

Max Activating Token Index: 13

Text #17

Max Range: 1.5562. Min Range: -1.5562

Max Act: 1.0218. Min Act: -0.0000

Data Index: 1274467 (C4 (Web Text))

Max Activating Token Index: 641

Text #18

Max Range: 1.5562. Min Range: -1.5562

Max Act: 1.0749. Min Act: -0.0000

Data Index: 630473 (C4 (Web Text))

Max Activating Token Index: 502

Text #19

Max Range: 1.5562. Min Range: -1.5562

Max Act: 0.9713. Min Act: -0.0000

Data Index: 642153 (C4 (Web Text))

Max Activating Token Index: 592