Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 235 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0768. Min Act: -0.0002

Data Index: 442265 (C4 (Web Text))

Max Activating Token Index: 112

Text #1

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0761. Min Act: -0.0002

Data Index: 568608 (C4 (Web Text))

Max Activating Token Index: 44

Text #2

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0752. Min Act: -0.0001

Data Index: 729660 (C4 (Web Text))

Max Activating Token Index: 135

Text #3

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0714. Min Act: -0.0002

Data Index: 272042 (C4 (Web Text))

Max Activating Token Index: 127

Text #4

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0698. Min Act: -0.0002

Data Index: 668913 (C4 (Web Text))

Max Activating Token Index: 51

Text #5

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0693. Min Act: -0.0002

Data Index: 340463 (C4 (Web Text))

Max Activating Token Index: 22

Text #6

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0693. Min Act: -0.0002

Data Index: 231912 (C4 (Web Text))

Max Activating Token Index: 557

Text #7

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0706. Min Act: -0.0002

Data Index: 650549 (C4 (Web Text))

Max Activating Token Index: 168

Text #8

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0654. Min Act: -0.0002

Data Index: 253746 (C4 (Web Text))

Max Activating Token Index: 658

Text #9

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0667. Min Act: -0.0001

Data Index: 1070193 (C4 (Web Text))

Max Activating Token Index: 590

Text #10

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0649. Min Act: -0.0001

Data Index: 784317 (C4 (Web Text))

Max Activating Token Index: 161

Text #11

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0665. Min Act: -0.0002

Data Index: 599343 (C4 (Web Text))

Max Activating Token Index: 50

Text #12

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0657. Min Act: -0.0002

Data Index: 641566 (C4 (Web Text))

Max Activating Token Index: 38

Text #13

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0657. Min Act: -0.0001

Data Index: 166379 (C4 (Web Text))

Max Activating Token Index: 242

Text #14

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0651. Min Act: -0.0002

Data Index: 935099 (C4 (Web Text))

Max Activating Token Index: 962

Text #15

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0636. Min Act: -0.0002

Data Index: 631354 (C4 (Web Text))

Max Activating Token Index: 279

Text #16

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0641. Min Act: -0.0002

Data Index: 186869 (C4 (Web Text))

Max Activating Token Index: 203

Text #17

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0664. Min Act: -0.0002

Data Index: 981086 (C4 (Web Text))

Max Activating Token Index: 93

Text #18

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0632. Min Act: -0.0002

Data Index: 1226815 (C4 (Web Text))

Max Activating Token Index: 173

Text #19

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0605. Min Act: -0.0002

Data Index: 98882 (C4 (Web Text))

Max Activating Token Index: 298