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

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

Neuron 3203 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0980. Min Act: -0.0000

Data Index: 899366 (C4 (Web Text))

Max Activating Token Index: 98

Text #1

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0866. Min Act: -0.0000

Data Index: 191944 (C4 (Web Text))

Max Activating Token Index: 302

Text #2

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0846. Min Act: -0.0000

Data Index: 61020 (C4 (Web Text))

Max Activating Token Index: 1005

Text #3

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0801. Min Act: -0.0000

Data Index: 920807 (C4 (Web Text))

Max Activating Token Index: 271

Text #4

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0704. Min Act: -0.0000

Data Index: 92469 (C4 (Web Text))

Max Activating Token Index: 286

Text #5

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0799. Min Act: -0.0000

Data Index: 761451 (C4 (Web Text))

Max Activating Token Index: 525

Text #6

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0696. Min Act: -0.0000

Data Index: 511178 (C4 (Web Text))

Max Activating Token Index: 895

Text #7

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0748. Min Act: -0.0000

Data Index: 13495 (C4 (Web Text))

Max Activating Token Index: 149

Text #8

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0766. Min Act: -0.0000

Data Index: 613407 (C4 (Web Text))

Max Activating Token Index: 529

Text #9

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0759. Min Act: -0.0000

Data Index: 1263559 (C4 (Web Text))

Max Activating Token Index: 342

Text #10

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0749. Min Act: -0.0000

Data Index: 927509 (C4 (Web Text))

Max Activating Token Index: 873

Text #11

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0746. Min Act: -0.0000

Data Index: 278130 (C4 (Web Text))

Max Activating Token Index: 1016

Text #12

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0712. Min Act: -0.0000

Data Index: 75785 (C4 (Web Text))

Max Activating Token Index: 899

Text #13

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0693. Min Act: -0.0000

Data Index: 881342 (C4 (Web Text))

Max Activating Token Index: 140

Text #14

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0657. Min Act: -0.0000

Data Index: 205058 (C4 (Web Text))

Max Activating Token Index: 189

Text #15

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0721. Min Act: -0.0000

Data Index: 816607 (C4 (Web Text))

Max Activating Token Index: 840

Text #16

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0714. Min Act: -0.0000

Data Index: 149077 (C4 (Web Text))

Max Activating Token Index: 783

Text #17

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0719. Min Act: -0.0000

Data Index: 888084 (C4 (Web Text))

Max Activating Token Index: 963

Text #18

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0702. Min Act: -0.0000

Data Index: 1020411 (C4 (Web Text))

Max Activating Token Index: 417

Text #19

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0728. Min Act: -0.0000

Data Index: 304522 (C4 (Web Text))

Max Activating Token Index: 748