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

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

Neuron 3609 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.8495. Min Range: -6.8495

Max Act: 6.8495. Min Act: -0.0000

Data Index: 531357 (C4 (Web Text))

Max Activating Token Index: 781

Text #1

Max Range: 6.8495. Min Range: -6.8495

Max Act: 6.7375. Min Act: -0.0000

Data Index: 550524 (C4 (Web Text))

Max Activating Token Index: 326

Text #2

Max Range: 6.8495. Min Range: -6.8495

Max Act: 6.1763. Min Act: -0.0000

Data Index: 236219 (C4 (Web Text))

Max Activating Token Index: 575

Text #3

Max Range: 6.8495. Min Range: -6.8495

Max Act: 6.0259. Min Act: -0.0000

Data Index: 939647 (C4 (Web Text))

Max Activating Token Index: 993

Text #4

Max Range: 6.8495. Min Range: -6.8495

Max Act: 6.3589. Min Act: -0.0000

Data Index: 746477 (C4 (Web Text))

Max Activating Token Index: 244

Text #5

Max Range: 6.8495. Min Range: -6.8495

Max Act: 6.1715. Min Act: -0.0000

Data Index: 833779 (C4 (Web Text))

Max Activating Token Index: 556

Text #6

Max Range: 6.8495. Min Range: -6.8495

Max Act: 6.1470. Min Act: -0.0000

Data Index: 1249159 (C4 (Web Text))

Max Activating Token Index: 295

Text #7

Max Range: 6.8495. Min Range: -6.8495

Max Act: 6.0780. Min Act: -0.0000

Data Index: 774447 (C4 (Web Text))

Max Activating Token Index: 161

Text #8

Max Range: 6.8495. Min Range: -6.8495

Max Act: 6.2087. Min Act: -0.0000

Data Index: 1036547 (C4 (Web Text))

Max Activating Token Index: 917

Text #9

Max Range: 6.8495. Min Range: -6.8495

Max Act: 5.9979. Min Act: -0.0000

Data Index: 1257363 (C4 (Web Text))

Max Activating Token Index: 651

Text #10

Max Range: 6.8495. Min Range: -6.8495

Max Act: 5.9940. Min Act: -0.0000

Data Index: 599713 (C4 (Web Text))

Max Activating Token Index: 114

Text #11

Max Range: 6.8495. Min Range: -6.8495

Max Act: 5.9272. Min Act: -0.0000

Data Index: 742278 (C4 (Web Text))

Max Activating Token Index: 777

Text #12

Max Range: 6.8495. Min Range: -6.8495

Max Act: 5.8473. Min Act: -0.0000

Data Index: 698176 (C4 (Web Text))

Max Activating Token Index: 95

Text #13

Max Range: 6.8495. Min Range: -6.8495

Max Act: 5.6425. Min Act: -0.0000

Data Index: 552926 (C4 (Web Text))

Max Activating Token Index: 910

Text #14

Max Range: 6.8495. Min Range: -6.8495

Max Act: 5.7927. Min Act: -0.0000

Data Index: 187928 (C4 (Web Text))

Max Activating Token Index: 476

Text #15

Max Range: 6.8495. Min Range: -6.8495

Max Act: 5.7947. Min Act: -0.0000

Data Index: 434947 (C4 (Web Text))

Max Activating Token Index: 719

Text #16

Max Range: 6.8495. Min Range: -6.8495

Max Act: 5.5829. Min Act: -0.0000

Data Index: 1317609 (C4 (Web Text))

Max Activating Token Index: 194

Text #17

Max Range: 6.8495. Min Range: -6.8495

Max Act: 5.7453. Min Act: -0.0000

Data Index: 1257528 (C4 (Web Text))

Max Activating Token Index: 75

Text #18

Max Range: 6.8495. Min Range: -6.8495

Max Act: 5.4803. Min Act: -0.0000

Data Index: 58659 (C4 (Web Text))

Max Activating Token Index: 749

Text #19

Max Range: 6.8495. Min Range: -6.8495

Max Act: 5.6385. Min Act: -0.0000

Data Index: 1167700 (C4 (Web Text))

Max Activating Token Index: 985