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

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

Neuron 2265 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: 0.1014. Min Range: -0.1014

Max Act: 0.1009. Min Act: -0.0002

Data Index: 191276 (C4 (Web Text))

Max Activating Token Index: 436

Text #1

Max Range: 0.1014. Min Range: -0.1014

Max Act: 0.0990. Min Act: -0.0002

Data Index: 490304 (C4 (Web Text))

Max Activating Token Index: 567

Text #2

Max Range: 0.1014. Min Range: -0.1014

Max Act: 0.1014. Min Act: -0.0002

Data Index: 416499 (C4 (Web Text))

Max Activating Token Index: 92

Text #3

Max Range: 0.1014. Min Range: -0.1014

Max Act: 0.0972. Min Act: -0.0002

Data Index: 260846 (C4 (Web Text))

Max Activating Token Index: 776

Text #4

Max Range: 0.1014. Min Range: -0.1014

Max Act: 0.0943. Min Act: -0.0002

Data Index: 1299359 (C4 (Web Text))

Max Activating Token Index: 560

Text #5

Max Range: 0.1014. Min Range: -0.1014

Max Act: 0.0935. Min Act: -0.0002

Data Index: 894990 (C4 (Web Text))

Max Activating Token Index: 694

Text #6

Max Range: 0.1014. Min Range: -0.1014

Max Act: 0.0931. Min Act: -0.0002

Data Index: 328375 (C4 (Web Text))

Max Activating Token Index: 642

Text #7

Max Range: 0.1014. Min Range: -0.1014

Max Act: 0.0911. Min Act: -0.0002

Data Index: 183638 (C4 (Web Text))

Max Activating Token Index: 223

Text #8

Max Range: 0.1014. Min Range: -0.1014

Max Act: 0.0887. Min Act: -0.0002

Data Index: 1319407 (C4 (Web Text))

Max Activating Token Index: 736

Text #9

Max Range: 0.1014. Min Range: -0.1014

Max Act: 0.0888. Min Act: -0.0002

Data Index: 735728 (C4 (Web Text))

Max Activating Token Index: 387

Text #10

Max Range: 0.1014. Min Range: -0.1014

Max Act: 0.0883. Min Act: -0.0002

Data Index: 372068 (C4 (Web Text))

Max Activating Token Index: 615

Text #11

Max Range: 0.1014. Min Range: -0.1014

Max Act: 0.0877. Min Act: -0.0002

Data Index: 276860 (C4 (Web Text))

Max Activating Token Index: 256

Text #12

Max Range: 0.1014. Min Range: -0.1014

Max Act: 0.0908. Min Act: -0.0002

Data Index: 886949 (C4 (Web Text))

Max Activating Token Index: 518

Text #13

Max Range: 0.1014. Min Range: -0.1014

Max Act: 0.0870. Min Act: -0.0002

Data Index: 1247768 (C4 (Web Text))

Max Activating Token Index: 225

Text #14

Max Range: 0.1014. Min Range: -0.1014

Max Act: 0.0876. Min Act: -0.0002

Data Index: 998534 (C4 (Web Text))

Max Activating Token Index: 816

Text #15

Max Range: 0.1014. Min Range: -0.1014

Max Act: 0.0900. Min Act: -0.0002

Data Index: 616610 (C4 (Web Text))

Max Activating Token Index: 216

Text #16

Max Range: 0.1014. Min Range: -0.1014

Max Act: 0.0892. Min Act: -0.0002

Data Index: 831902 (C4 (Web Text))

Max Activating Token Index: 856

Text #17

Max Range: 0.1014. Min Range: -0.1014

Max Act: 0.0835. Min Act: -0.0002

Data Index: 1015850 (C4 (Web Text))

Max Activating Token Index: 317

Text #18

Max Range: 0.1014. Min Range: -0.1014

Max Act: 0.0891. Min Act: -0.0002

Data Index: 1325797 (C4 (Web Text))

Max Activating Token Index: 616

Text #19

Max Range: 0.1014. Min Range: -0.1014

Max Act: 0.0859. Min Act: -0.0002

Data Index: 48228 (C4 (Web Text))

Max Activating Token Index: 173