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

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

Neuron 1135 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6858. Min Range: -0.6858

Max Act: 0.6843. Min Act: 0.0000

Data Index: 406298 (C4 (Web Text))

Max Activating Token Index: 541

Text #1

Max Range: 0.6858. Min Range: -0.6858

Max Act: 0.6858. Min Act: -0.0000

Data Index: 160146 (C4 (Web Text))

Max Activating Token Index: 221

Text #2

Max Range: 0.6858. Min Range: -0.6858

Max Act: 0.6192. Min Act: -0.0000

Data Index: 801447 (C4 (Web Text))

Max Activating Token Index: 852

Text #3

Max Range: 0.6858. Min Range: -0.6858

Max Act: 0.5959. Min Act: -0.0000

Data Index: 456855 (C4 (Web Text))

Max Activating Token Index: 35

Text #4

Max Range: 0.6858. Min Range: -0.6858

Max Act: 0.5979. Min Act: -0.0000

Data Index: 1223373 (C4 (Web Text))

Max Activating Token Index: 952

Text #5

Max Range: 0.6858. Min Range: -0.6858

Max Act: 0.6107. Min Act: 0.0002

Data Index: 126395 (C4 (Web Text))

Max Activating Token Index: 236

Text #6

Max Range: 0.6858. Min Range: -0.6858

Max Act: 0.5841. Min Act: -0.0000

Data Index: 84439 (C4 (Web Text))

Max Activating Token Index: 661

Text #7

Max Range: 0.6858. Min Range: -0.6858

Max Act: 0.5955. Min Act: -0.0000

Data Index: 658691 (C4 (Web Text))

Max Activating Token Index: 894

Text #8

Max Range: 0.6858. Min Range: -0.6858

Max Act: 0.5532. Min Act: -0.0000

Data Index: 1196809 (C4 (Web Text))

Max Activating Token Index: 487

Text #9

Max Range: 0.6858. Min Range: -0.6858

Max Act: 0.5635. Min Act: -0.0000

Data Index: 204372 (C4 (Web Text))

Max Activating Token Index: 671

Text #10

Max Range: 0.6858. Min Range: -0.6858

Max Act: 0.5802. Min Act: -0.0000

Data Index: 250820 (C4 (Web Text))

Max Activating Token Index: 765

Text #11

Max Range: 0.6858. Min Range: -0.6858

Max Act: 0.5845. Min Act: -0.0000

Data Index: 32296 (C4 (Web Text))

Max Activating Token Index: 686

Text #12

Max Range: 0.6858. Min Range: -0.6858

Max Act: 0.5330. Min Act: -0.0000

Data Index: 1154595 (C4 (Web Text))

Max Activating Token Index: 21

Text #13

Max Range: 0.6858. Min Range: -0.6858

Max Act: 0.5084. Min Act: -0.0000

Data Index: 636349 (C4 (Web Text))

Max Activating Token Index: 327

Text #14

Max Range: 0.6858. Min Range: -0.6858

Max Act: 0.5394. Min Act: -0.0000

Data Index: 1315896 (C4 (Web Text))

Max Activating Token Index: 798

Text #15

Max Range: 0.6858. Min Range: -0.6858

Max Act: 0.5101. Min Act: -0.0000

Data Index: 413724 (C4 (Web Text))

Max Activating Token Index: 617

Text #16

Max Range: 0.6858. Min Range: -0.6858

Max Act: 0.4954. Min Act: -0.0000

Data Index: 984916 (C4 (Web Text))

Max Activating Token Index: 668

Text #17

Max Range: 0.6858. Min Range: -0.6858

Max Act: 0.4782. Min Act: -0.0000

Data Index: 167668 (C4 (Web Text))

Max Activating Token Index: 811

Text #18

Max Range: 0.6858. Min Range: -0.6858

Max Act: 0.5078. Min Act: -0.0000

Data Index: 845745 (C4 (Web Text))

Max Activating Token Index: 1014

Text #19

Max Range: 0.6858. Min Range: -0.6858

Max Act: 0.4924. Min Act: -0.0000

Data Index: 188624 (C4 (Web Text))

Max Activating Token Index: 642