Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3285 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.6892. Min Range: -1.6892

Max Act: 1.6892. Min Act: -0.0000

Data Index: 358492 (C4 (Web Text))

Max Activating Token Index: 870

Text #1

Max Range: 1.6892. Min Range: -1.6892

Max Act: 1.6812. Min Act: -0.0000

Data Index: 617375 (C4 (Web Text))

Max Activating Token Index: 743

Text #2

Max Range: 1.6892. Min Range: -1.6892

Max Act: 1.6496. Min Act: -0.0000

Data Index: 1294815 (C4 (Web Text))

Max Activating Token Index: 25

Text #3

Max Range: 1.6892. Min Range: -1.6892

Max Act: 1.6876. Min Act: -0.0000

Data Index: 366880 (C4 (Web Text))

Max Activating Token Index: 157

Text #4

Max Range: 1.6892. Min Range: -1.6892

Max Act: 1.5026. Min Act: -0.0000

Data Index: 592989 (C4 (Web Text))

Max Activating Token Index: 336

Text #5

Max Range: 1.6892. Min Range: -1.6892

Max Act: 1.5806. Min Act: -0.0000

Data Index: 1031526 (C4 (Web Text))

Max Activating Token Index: 613

Text #6

Max Range: 1.6892. Min Range: -1.6892

Max Act: 1.4650. Min Act: -0.0000

Data Index: 1333298 (C4 (Web Text))

Max Activating Token Index: 922

Text #7

Max Range: 1.6892. Min Range: -1.6892

Max Act: 1.5744. Min Act: -0.0000

Data Index: 245896 (C4 (Web Text))

Max Activating Token Index: 665

Text #8

Max Range: 1.6892. Min Range: -1.6892

Max Act: 1.5842. Min Act: -0.0000

Data Index: 1284855 (C4 (Web Text))

Max Activating Token Index: 261

Text #9

Max Range: 1.6892. Min Range: -1.6892

Max Act: 1.3535. Min Act: -0.0000

Data Index: 921821 (C4 (Web Text))

Max Activating Token Index: 155

Text #10

Max Range: 1.6892. Min Range: -1.6892

Max Act: 1.3961. Min Act: -0.0000

Data Index: 1265008 (C4 (Web Text))

Max Activating Token Index: 103

Text #11

Max Range: 1.6892. Min Range: -1.6892

Max Act: 1.4137. Min Act: -0.0000

Data Index: 1110489 (C4 (Web Text))

Max Activating Token Index: 380

Text #12

Max Range: 1.6892. Min Range: -1.6892

Max Act: 1.4486. Min Act: -0.0000

Data Index: 970783 (C4 (Web Text))

Max Activating Token Index: 747

Text #13

Max Range: 1.6892. Min Range: -1.6892

Max Act: 1.4489. Min Act: -0.0000

Data Index: 965036 (C4 (Web Text))

Max Activating Token Index: 380

Text #14

Max Range: 1.6892. Min Range: -1.6892

Max Act: 1.3983. Min Act: -0.0000

Data Index: 357993 (C4 (Web Text))

Max Activating Token Index: 565

Text #15

Max Range: 1.6892. Min Range: -1.6892

Max Act: 1.4363. Min Act: -0.0000

Data Index: 882511 (C4 (Web Text))

Max Activating Token Index: 924

Text #16

Max Range: 1.6892. Min Range: -1.6892

Max Act: 1.4298. Min Act: -0.0000

Data Index: 566996 (C4 (Web Text))

Max Activating Token Index: 516

Text #17

Max Range: 1.6892. Min Range: -1.6892

Max Act: 1.4258. Min Act: -0.0000

Data Index: 1170922 (C4 (Web Text))

Max Activating Token Index: 108

Text #18

Max Range: 1.6892. Min Range: -1.6892

Max Act: 1.5252. Min Act: -0.0000

Data Index: 569316 (C4 (Web Text))

Max Activating Token Index: 260

Text #19

Max Range: 1.6892. Min Range: -1.6892

Max Act: 1.3127. Min Act: -0.0000

Data Index: 1148715 (C4 (Web Text))

Max Activating Token Index: 840