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

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

Neuron 1330 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7720. Min Range: -0.7720

Max Act: 0.7053. Min Act: -0.0000

Data Index: 1108651 (C4 (Web Text))

Max Activating Token Index: 801

Text #1

Max Range: 0.7720. Min Range: -0.7720

Max Act: 0.6949. Min Act: -0.0000

Data Index: 910140 (C4 (Web Text))

Max Activating Token Index: 550

Text #2

Max Range: 0.7720. Min Range: -0.7720

Max Act: 0.7720. Min Act: -0.0000

Data Index: 1103562 (C4 (Web Text))

Max Activating Token Index: 363

Text #3

Max Range: 0.7720. Min Range: -0.7720

Max Act: 0.5948. Min Act: -0.0000

Data Index: 850709 (C4 (Web Text))

Max Activating Token Index: 859

Text #4

Max Range: 0.7720. Min Range: -0.7720

Max Act: 0.5272. Min Act: -0.0000

Data Index: 700005 (C4 (Web Text))

Max Activating Token Index: 702

Text #5

Max Range: 0.7720. Min Range: -0.7720

Max Act: 0.5680. Min Act: -0.0000

Data Index: 1257197 (C4 (Web Text))

Max Activating Token Index: 610

Text #6

Max Range: 0.7720. Min Range: -0.7720

Max Act: 0.5544. Min Act: -0.0000

Data Index: 298336 (C4 (Web Text))

Max Activating Token Index: 773

Text #7

Max Range: 0.7720. Min Range: -0.7720

Max Act: 0.5516. Min Act: -0.0000

Data Index: 764128 (C4 (Web Text))

Max Activating Token Index: 307

Text #8

Max Range: 0.7720. Min Range: -0.7720

Max Act: 0.5112. Min Act: -0.0000

Data Index: 486626 (C4 (Web Text))

Max Activating Token Index: 27

Text #9

Max Range: 0.7720. Min Range: -0.7720

Max Act: 0.5165. Min Act: -0.0000

Data Index: 1184432 (C4 (Web Text))

Max Activating Token Index: 743

Text #10

Max Range: 0.7720. Min Range: -0.7720

Max Act: 0.4893. Min Act: -0.0000

Data Index: 452087 (C4 (Web Text))

Max Activating Token Index: 894

Text #11

Max Range: 0.7720. Min Range: -0.7720

Max Act: 0.4903. Min Act: -0.0000

Data Index: 738528 (C4 (Web Text))

Max Activating Token Index: 501

Text #12

Max Range: 0.7720. Min Range: -0.7720

Max Act: 0.4920. Min Act: -0.0000

Data Index: 589417 (C4 (Web Text))

Max Activating Token Index: 53

Text #13

Max Range: 0.7720. Min Range: -0.7720

Max Act: 0.4692. Min Act: -0.0000

Data Index: 543593 (C4 (Web Text))

Max Activating Token Index: 183

Text #14

Max Range: 0.7720. Min Range: -0.7720

Max Act: 0.4729. Min Act: -0.0000

Data Index: 1318327 (C4 (Web Text))

Max Activating Token Index: 490

Text #15

Max Range: 0.7720. Min Range: -0.7720

Max Act: 0.4606. Min Act: -0.0000

Data Index: 502667 (C4 (Web Text))

Max Activating Token Index: 734

Text #16

Max Range: 0.7720. Min Range: -0.7720

Max Act: 0.4581. Min Act: -0.0000

Data Index: 114931 (C4 (Web Text))

Max Activating Token Index: 657

Text #17

Max Range: 0.7720. Min Range: -0.7720

Max Act: 0.4285. Min Act: -0.0000

Data Index: 405025 (C4 (Web Text))

Max Activating Token Index: 807

Text #18

Max Range: 0.7720. Min Range: -0.7720

Max Act: 0.4479. Min Act: -0.0000

Data Index: 258860 (C4 (Web Text))

Max Activating Token Index: 774

Text #19

Max Range: 0.7720. Min Range: -0.7720

Max Act: 0.4677. Min Act: -0.0000

Data Index: 476524 (C4 (Web Text))

Max Activating Token Index: 106