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

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

Neuron 3283 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: 0.1027. Min Range: -0.1027

Max Act: 0.1027. Min Act: -0.0000

Data Index: 810204 (C4 (Web Text))

Max Activating Token Index: 623

Text #1

Max Range: 0.1027. Min Range: -0.1027

Max Act: 0.0862. Min Act: -0.0000

Data Index: 424494 (C4 (Web Text))

Max Activating Token Index: 16

Text #2

Max Range: 0.1027. Min Range: -0.1027

Max Act: 0.0784. Min Act: -0.0000

Data Index: 291503 (C4 (Web Text))

Max Activating Token Index: 49

Text #3

Max Range: 0.1027. Min Range: -0.1027

Max Act: 0.0858. Min Act: -0.0000

Data Index: 707580 (C4 (Web Text))

Max Activating Token Index: 827

Text #4

Max Range: 0.1027. Min Range: -0.1027

Max Act: 0.0821. Min Act: -0.0000

Data Index: 840562 (C4 (Web Text))

Max Activating Token Index: 288

Text #5

Max Range: 0.1027. Min Range: -0.1027

Max Act: 0.0797. Min Act: -0.0000

Data Index: 123956 (C4 (Web Text))

Max Activating Token Index: 957

Text #6

Max Range: 0.1027. Min Range: -0.1027

Max Act: 0.0745. Min Act: -0.0000

Data Index: 25699 (C4 (Web Text))

Max Activating Token Index: 16

Text #7

Max Range: 0.1027. Min Range: -0.1027

Max Act: 0.0760. Min Act: -0.0000

Data Index: 345351 (C4 (Web Text))

Max Activating Token Index: 44

Text #8

Max Range: 0.1027. Min Range: -0.1027

Max Act: 0.0742. Min Act: -0.0000

Data Index: 275380 (C4 (Web Text))

Max Activating Token Index: 546

Text #9

Max Range: 0.1027. Min Range: -0.1027

Max Act: 0.0719. Min Act: -0.0000

Data Index: 1097136 (C4 (Web Text))

Max Activating Token Index: 135

Text #10

Max Range: 0.1027. Min Range: -0.1027

Max Act: 0.0678. Min Act: -0.0000

Data Index: 883255 (C4 (Web Text))

Max Activating Token Index: 12

Text #11

Max Range: 0.1027. Min Range: -0.1027

Max Act: 0.0679. Min Act: -0.0000

Data Index: 281491 (C4 (Web Text))

Max Activating Token Index: 108

Text #12

Max Range: 0.1027. Min Range: -0.1027

Max Act: 0.0701. Min Act: -0.0000

Data Index: 616307 (C4 (Web Text))

Max Activating Token Index: 53

Text #13

Max Range: 0.1027. Min Range: -0.1027

Max Act: 0.0692. Min Act: -0.0000

Data Index: 268910 (C4 (Web Text))

Max Activating Token Index: 492

Text #14

Max Range: 0.1027. Min Range: -0.1027

Max Act: 0.0686. Min Act: -0.0000

Data Index: 19941 (C4 (Web Text))

Max Activating Token Index: 31

Text #15

Max Range: 0.1027. Min Range: -0.1027

Max Act: 0.0686. Min Act: -0.0000

Data Index: 1264548 (C4 (Web Text))

Max Activating Token Index: 491

Text #16

Max Range: 0.1027. Min Range: -0.1027

Max Act: 0.0627. Min Act: -0.0000

Data Index: 728263 (C4 (Web Text))

Max Activating Token Index: 109

Text #17

Max Range: 0.1027. Min Range: -0.1027

Max Act: 0.0620. Min Act: -0.0000

Data Index: 120641 (C4 (Web Text))

Max Activating Token Index: 571

Text #18

Max Range: 0.1027. Min Range: -0.1027

Max Act: 0.0655. Min Act: -0.0000

Data Index: 1128420 (C4 (Web Text))

Max Activating Token Index: 119

Text #19

Max Range: 0.1027. Min Range: -0.1027

Max Act: 0.0648. Min Act: -0.0000

Data Index: 344975 (C4 (Web Text))

Max Activating Token Index: 290