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

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

Neuron 409 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6656. Min Range: -1.6656

Max Act: 1.6656. Min Act: -0.0000

Data Index: 325211 (C4 (Web Text))

Max Activating Token Index: 175

Text #1

Max Range: 1.6656. Min Range: -1.6656

Max Act: 1.5994. Min Act: 0.0000

Data Index: 1128188 (C4 (Web Text))

Max Activating Token Index: 843

Text #2

Max Range: 1.6656. Min Range: -1.6656

Max Act: 1.5594. Min Act: -0.0000

Data Index: 1187553 (C4 (Web Text))

Max Activating Token Index: 389

Text #3

Max Range: 1.6656. Min Range: -1.6656

Max Act: 1.4474. Min Act: -0.0000

Data Index: 608592 (C4 (Web Text))

Max Activating Token Index: 233

Text #4

Max Range: 1.6656. Min Range: -1.6656

Max Act: 1.3585. Min Act: -0.0000

Data Index: 1103553 (C4 (Web Text))

Max Activating Token Index: 998

Text #5

Max Range: 1.6656. Min Range: -1.6656

Max Act: 1.3412. Min Act: -0.0000

Data Index: 385785 (C4 (Web Text))

Max Activating Token Index: 945

Text #6

Max Range: 1.6656. Min Range: -1.6656

Max Act: 1.3993. Min Act: -0.0000

Data Index: 638906 (C4 (Web Text))

Max Activating Token Index: 324

Text #7

Max Range: 1.6656. Min Range: -1.6656

Max Act: 1.2718. Min Act: -0.0000

Data Index: 1304503 (C4 (Web Text))

Max Activating Token Index: 375

Text #8

Max Range: 1.6656. Min Range: -1.6656

Max Act: 1.2624. Min Act: -0.0000

Data Index: 599657 (C4 (Web Text))

Max Activating Token Index: 590

Text #9

Max Range: 1.6656. Min Range: -1.6656

Max Act: 1.2508. Min Act: -0.0000

Data Index: 523093 (C4 (Web Text))

Max Activating Token Index: 853

Text #10

Max Range: 1.6656. Min Range: -1.6656

Max Act: 1.2420. Min Act: -0.0000

Data Index: 538975 (C4 (Web Text))

Max Activating Token Index: 145

Text #11

Max Range: 1.6656. Min Range: -1.6656

Max Act: 1.0947. Min Act: -0.0000

Data Index: 857280 (C4 (Web Text))

Max Activating Token Index: 692

Text #12

Max Range: 1.6656. Min Range: -1.6656

Max Act: 1.1462. Min Act: -0.0000

Data Index: 1320737 (C4 (Web Text))

Max Activating Token Index: 116

Text #13

Max Range: 1.6656. Min Range: -1.6656

Max Act: 1.1453. Min Act: -0.0000

Data Index: 73199 (C4 (Web Text))

Max Activating Token Index: 128

Text #14

Max Range: 1.6656. Min Range: -1.6656

Max Act: 1.1384. Min Act: -0.0000

Data Index: 587079 (C4 (Web Text))

Max Activating Token Index: 667

Text #15

Max Range: 1.6656. Min Range: -1.6656

Max Act: 1.1357. Min Act: -0.0000

Data Index: 875087 (C4 (Web Text))

Max Activating Token Index: 645

Text #16

Max Range: 1.6656. Min Range: -1.6656

Max Act: 1.1953. Min Act: -0.0000

Data Index: 1126460 (C4 (Web Text))

Max Activating Token Index: 199

Text #17

Max Range: 1.6656. Min Range: -1.6656

Max Act: 1.0383. Min Act: -0.0000

Data Index: 875886 (C4 (Web Text))

Max Activating Token Index: 833

Text #18

Max Range: 1.6656. Min Range: -1.6656

Max Act: 1.1050. Min Act: -0.0000

Data Index: 1352069 (C4 (Web Text))

Max Activating Token Index: 20

Text #19

Max Range: 1.6656. Min Range: -1.6656

Max Act: 1.0997. Min Act: -0.0000

Data Index: 258576 (C4 (Web Text))

Max Activating Token Index: 196