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

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

Neuron 4573 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3587. Min Range: -0.3587

Max Act: 0.3587. Min Act: -0.0000

Data Index: 1305001 (C4 (Web Text))

Max Activating Token Index: 117

Text #1

Max Range: 0.3587. Min Range: -0.3587

Max Act: 0.3430. Min Act: -0.0000

Data Index: 494816 (C4 (Web Text))

Max Activating Token Index: 723

Text #2

Max Range: 0.3587. Min Range: -0.3587

Max Act: 0.3251. Min Act: -0.0000

Data Index: 107259 (C4 (Web Text))

Max Activating Token Index: 400

Text #3

Max Range: 0.3587. Min Range: -0.3587

Max Act: 0.3285. Min Act: -0.0000

Data Index: 879440 (C4 (Web Text))

Max Activating Token Index: 809

Text #4

Max Range: 0.3587. Min Range: -0.3587

Max Act: 0.3141. Min Act: -0.0000

Data Index: 108710 (C4 (Web Text))

Max Activating Token Index: 143

Text #5

Max Range: 0.3587. Min Range: -0.3587

Max Act: 0.3171. Min Act: -0.0000

Data Index: 492779 (C4 (Web Text))

Max Activating Token Index: 718

Text #6

Max Range: 0.3587. Min Range: -0.3587

Max Act: 0.3049. Min Act: -0.0000

Data Index: 464096 (C4 (Web Text))

Max Activating Token Index: 155

Text #7

Max Range: 0.3587. Min Range: -0.3587

Max Act: 0.3145. Min Act: -0.0000

Data Index: 916565 (C4 (Web Text))

Max Activating Token Index: 965

Text #8

Max Range: 0.3587. Min Range: -0.3587

Max Act: 0.3119. Min Act: -0.0000

Data Index: 299624 (C4 (Web Text))

Max Activating Token Index: 565

Text #9

Max Range: 0.3587. Min Range: -0.3587

Max Act: 0.3042. Min Act: -0.0000

Data Index: 622587 (C4 (Web Text))

Max Activating Token Index: 703

Text #10

Max Range: 0.3587. Min Range: -0.3587

Max Act: 0.3047. Min Act: -0.0000

Data Index: 20123 (C4 (Web Text))

Max Activating Token Index: 557

Text #11

Max Range: 0.3587. Min Range: -0.3587

Max Act: 0.2885. Min Act: -0.0000

Data Index: 475201 (C4 (Web Text))

Max Activating Token Index: 945

Text #12

Max Range: 0.3587. Min Range: -0.3587

Max Act: 0.2888. Min Act: -0.0000

Data Index: 449276 (C4 (Web Text))

Max Activating Token Index: 256

Text #13

Max Range: 0.3587. Min Range: -0.3587

Max Act: 0.2769. Min Act: -0.0000

Data Index: 239596 (C4 (Web Text))

Max Activating Token Index: 616

Text #14

Max Range: 0.3587. Min Range: -0.3587

Max Act: 0.2856. Min Act: -0.0000

Data Index: 1211968 (C4 (Web Text))

Max Activating Token Index: 755

Text #15

Max Range: 0.3587. Min Range: -0.3587

Max Act: 0.2821. Min Act: -0.0000

Data Index: 479726 (C4 (Web Text))

Max Activating Token Index: 731

Text #16

Max Range: 0.3587. Min Range: -0.3587

Max Act: 0.2811. Min Act: -0.0000

Data Index: 868499 (C4 (Web Text))

Max Activating Token Index: 818

Text #17

Max Range: 0.3587. Min Range: -0.3587

Max Act: 0.2892. Min Act: -0.0000

Data Index: 969775 (C4 (Web Text))

Max Activating Token Index: 943

Text #18

Max Range: 0.3587. Min Range: -0.3587

Max Act: 0.2703. Min Act: -0.0000

Data Index: 80074 (C4 (Web Text))

Max Activating Token Index: 888

Text #19

Max Range: 0.3587. Min Range: -0.3587

Max Act: 0.2780. Min Act: -0.0000

Data Index: 1198713 (C4 (Web Text))

Max Activating Token Index: 43