Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1574 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.1137. Min Act: -0.0004

Data Index: 882312 (C4 (Web Text))

Max Activating Token Index: 738

Text #1

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.1090. Min Act: -0.0003

Data Index: 692902 (C4 (Web Text))

Max Activating Token Index: 908

Text #2

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0965. Min Act: -0.0003

Data Index: 1018784 (C4 (Web Text))

Max Activating Token Index: 955

Text #3

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0974. Min Act: -0.0003

Data Index: 1632582 (Python Code)

Max Activating Token Index: 86

Text #4

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0986. Min Act: -0.0003

Data Index: 520437 (C4 (Web Text))

Max Activating Token Index: 160

Text #5

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0965. Min Act: -0.0003

Data Index: 787852 (C4 (Web Text))

Max Activating Token Index: 857

Text #6

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0936. Min Act: -0.0003

Data Index: 267762 (C4 (Web Text))

Max Activating Token Index: 896

Text #7

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0943. Min Act: -0.0003

Data Index: 804863 (C4 (Web Text))

Max Activating Token Index: 237

Text #8

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0938. Min Act: -0.0004

Data Index: 346273 (C4 (Web Text))

Max Activating Token Index: 32

Text #9

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0894. Min Act: -0.0003

Data Index: 510588 (C4 (Web Text))

Max Activating Token Index: 10

Text #10

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0924. Min Act: -0.0003

Data Index: 1591452 (Python Code)

Max Activating Token Index: 972

Text #11

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0904. Min Act: -0.0003

Data Index: 460647 (C4 (Web Text))

Max Activating Token Index: 123

Text #12

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0838. Min Act: -0.0003

Data Index: 1642493 (Python Code)

Max Activating Token Index: 774

Text #13

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0909. Min Act: -0.0003

Data Index: 1186636 (C4 (Web Text))

Max Activating Token Index: 334

Text #14

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0885. Min Act: -0.0003

Data Index: 718402 (C4 (Web Text))

Max Activating Token Index: 200

Text #15

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0880. Min Act: -0.0003

Data Index: 1123264 (C4 (Web Text))

Max Activating Token Index: 878

Text #16

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0845. Min Act: -0.0003

Data Index: 632730 (C4 (Web Text))

Max Activating Token Index: 74

Text #17

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0838. Min Act: -0.0003

Data Index: 485314 (C4 (Web Text))

Max Activating Token Index: 227

Text #18

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0865. Min Act: -0.0003

Data Index: 444317 (C4 (Web Text))

Max Activating Token Index: 957

Text #19

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0814. Min Act: -0.0003

Data Index: 506595 (C4 (Web Text))

Max Activating Token Index: 905