Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 271 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0935. Min Act: -0.0003

Data Index: 35126 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0824. Min Act: -0.0003

Data Index: 169630 (C4 (Web Text))

Max Activating Token Index: 111

Text #2

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0791. Min Act: -0.0003

Data Index: 165999 (C4 (Web Text))

Max Activating Token Index: 895

Text #3

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0817. Min Act: -0.0003

Data Index: 121759 (C4 (Web Text))

Max Activating Token Index: 898

Text #4

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0839. Min Act: -0.0003

Data Index: 653137 (C4 (Web Text))

Max Activating Token Index: 779

Text #5

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0769. Min Act: -0.0003

Data Index: 553797 (C4 (Web Text))

Max Activating Token Index: 735

Text #6

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0785. Min Act: -0.0003

Data Index: 1161206 (C4 (Web Text))

Max Activating Token Index: 918

Text #7

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0781. Min Act: -0.0003

Data Index: 1000077 (C4 (Web Text))

Max Activating Token Index: 11

Text #8

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0763. Min Act: -0.0003

Data Index: 1033313 (C4 (Web Text))

Max Activating Token Index: 895

Text #9

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0769. Min Act: -0.0003

Data Index: 896609 (C4 (Web Text))

Max Activating Token Index: 736

Text #10

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0685. Min Act: -0.0003

Data Index: 124827 (C4 (Web Text))

Max Activating Token Index: 910

Text #11

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0706. Min Act: -0.0003

Data Index: 670229 (C4 (Web Text))

Max Activating Token Index: 112

Text #12

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0685. Min Act: -0.0003

Data Index: 901163 (C4 (Web Text))

Max Activating Token Index: 15

Text #13

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0685. Min Act: -0.0003

Data Index: 1244268 (C4 (Web Text))

Max Activating Token Index: 437

Text #14

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0791. Min Act: -0.0003

Data Index: 857626 (C4 (Web Text))

Max Activating Token Index: 88

Text #15

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0687. Min Act: -0.0003

Data Index: 65403 (C4 (Web Text))

Max Activating Token Index: 747

Text #16

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0730. Min Act: -0.0003

Data Index: 835280 (C4 (Web Text))

Max Activating Token Index: 54

Text #17

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0698. Min Act: -0.0003

Data Index: 683955 (C4 (Web Text))

Max Activating Token Index: 119

Text #18

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0709. Min Act: -0.0003

Data Index: 62627 (C4 (Web Text))

Max Activating Token Index: 718

Text #19

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0718. Min Act: -0.0003

Data Index: 1338071 (C4 (Web Text))

Max Activating Token Index: 352