Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3323 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.0012. Min Range: -2.0012

Max Act: 2.0012. Min Act: -0.0000

Data Index: 305153 (C4 (Web Text))

Max Activating Token Index: 13

Text #1

Max Range: 2.0012. Min Range: -2.0012

Max Act: 1.9540. Min Act: -0.0000

Data Index: 1086631 (C4 (Web Text))

Max Activating Token Index: 829

Text #2

Max Range: 2.0012. Min Range: -2.0012

Max Act: 1.9960. Min Act: -0.0000

Data Index: 473927 (C4 (Web Text))

Max Activating Token Index: 166

Text #3

Max Range: 2.0012. Min Range: -2.0012

Max Act: 1.8165. Min Act: -0.0000

Data Index: 1316261 (C4 (Web Text))

Max Activating Token Index: 106

Text #4

Max Range: 2.0012. Min Range: -2.0012

Max Act: 1.7157. Min Act: -0.0000

Data Index: 22937 (C4 (Web Text))

Max Activating Token Index: 8

Text #5

Max Range: 2.0012. Min Range: -2.0012

Max Act: 1.7193. Min Act: -0.0000

Data Index: 83786 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 2.0012. Min Range: -2.0012

Max Act: 1.7134. Min Act: -0.0000

Data Index: 325300 (C4 (Web Text))

Max Activating Token Index: 604

Text #7

Max Range: 2.0012. Min Range: -2.0012

Max Act: 1.7974. Min Act: -0.0000

Data Index: 601083 (C4 (Web Text))

Max Activating Token Index: 5

Text #8

Max Range: 2.0012. Min Range: -2.0012

Max Act: 1.7393. Min Act: -0.0000

Data Index: 1214312 (C4 (Web Text))

Max Activating Token Index: 296

Text #9

Max Range: 2.0012. Min Range: -2.0012

Max Act: 1.7038. Min Act: -0.0000

Data Index: 525934 (C4 (Web Text))

Max Activating Token Index: 147

Text #10

Max Range: 2.0012. Min Range: -2.0012

Max Act: 1.7833. Min Act: -0.0000

Data Index: 113995 (C4 (Web Text))

Max Activating Token Index: 25

Text #11

Max Range: 2.0012. Min Range: -2.0012

Max Act: 1.5871. Min Act: -0.0000

Data Index: 763020 (C4 (Web Text))

Max Activating Token Index: 26

Text #12

Max Range: 2.0012. Min Range: -2.0012

Max Act: 1.6737. Min Act: -0.0000

Data Index: 1333129 (C4 (Web Text))

Max Activating Token Index: 530

Text #13

Max Range: 2.0012. Min Range: -2.0012

Max Act: 1.5852. Min Act: -0.0000

Data Index: 990232 (C4 (Web Text))

Max Activating Token Index: 26

Text #14

Max Range: 2.0012. Min Range: -2.0012

Max Act: 1.6010. Min Act: -0.0000

Data Index: 496208 (C4 (Web Text))

Max Activating Token Index: 188

Text #15

Max Range: 2.0012. Min Range: -2.0012

Max Act: 1.6567. Min Act: -0.0000

Data Index: 1319790 (C4 (Web Text))

Max Activating Token Index: 59

Text #16

Max Range: 2.0012. Min Range: -2.0012

Max Act: 1.7611. Min Act: -0.0000

Data Index: 1008354 (C4 (Web Text))

Max Activating Token Index: 755

Text #17

Max Range: 2.0012. Min Range: -2.0012

Max Act: 1.7533. Min Act: -0.0000

Data Index: 885040 (C4 (Web Text))

Max Activating Token Index: 553

Text #18

Max Range: 2.0012. Min Range: -2.0012

Max Act: 1.6505. Min Act: -0.0000

Data Index: 50782 (C4 (Web Text))

Max Activating Token Index: 72

Text #19

Max Range: 2.0012. Min Range: -2.0012

Max Act: 1.6598. Min Act: -0.0000

Data Index: 372871 (C4 (Web Text))

Max Activating Token Index: 120