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

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

Neuron 3244 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.1567. Min Act: -0.0002

Data Index: 714815 (C4 (Web Text))

Max Activating Token Index: 454

Text #1

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.1240. Min Act: -0.0002

Data Index: 1237865 (C4 (Web Text))

Max Activating Token Index: 16

Text #2

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.1172. Min Act: -0.0002

Data Index: 860289 (C4 (Web Text))

Max Activating Token Index: 867

Text #3

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.0964. Min Act: -0.0002

Data Index: 492223 (C4 (Web Text))

Max Activating Token Index: 372

Text #4

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.0862. Min Act: -0.0002

Data Index: 1203612 (C4 (Web Text))

Max Activating Token Index: 182

Text #5

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.0827. Min Act: -0.0002

Data Index: 63723 (C4 (Web Text))

Max Activating Token Index: 535

Text #6

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.0837. Min Act: -0.0002

Data Index: 1354492 (C4 (Web Text))

Max Activating Token Index: 357

Text #7

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.0804. Min Act: -0.0002

Data Index: 1204272 (C4 (Web Text))

Max Activating Token Index: 157

Text #8

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.0797. Min Act: -0.0002

Data Index: 888993 (C4 (Web Text))

Max Activating Token Index: 110

Text #9

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.0783. Min Act: -0.0002

Data Index: 297825 (C4 (Web Text))

Max Activating Token Index: 549

Text #10

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.0787. Min Act: -0.0002

Data Index: 288322 (C4 (Web Text))

Max Activating Token Index: 823

Text #11

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.0780. Min Act: -0.0002

Data Index: 39607 (C4 (Web Text))

Max Activating Token Index: 446

Text #12

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.0745. Min Act: -0.0002

Data Index: 684410 (C4 (Web Text))

Max Activating Token Index: 517

Text #13

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.0743. Min Act: -0.0002

Data Index: 1336038 (C4 (Web Text))

Max Activating Token Index: 470

Text #14

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.0784. Min Act: -0.0002

Data Index: 1331563 (C4 (Web Text))

Max Activating Token Index: 525

Text #15

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.0777. Min Act: -0.0002

Data Index: 134242 (C4 (Web Text))

Max Activating Token Index: 142

Text #16

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.0777. Min Act: -0.0002

Data Index: 155736 (C4 (Web Text))

Max Activating Token Index: 54

Text #17

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.0683. Min Act: -0.0002

Data Index: 745363 (C4 (Web Text))

Max Activating Token Index: 720

Text #18

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.0706. Min Act: -0.0002

Data Index: 131040 (C4 (Web Text))

Max Activating Token Index: 520

Text #19

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.0677. Min Act: -0.0002

Data Index: 724767 (C4 (Web Text))

Max Activating Token Index: 479