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

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

Neuron 4606 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3916. Min Range: -2.3916

Max Act: 2.3916. Min Act: -0.0000

Data Index: 1214569 (C4 (Web Text))

Max Activating Token Index: 303

Text #1

Max Range: 2.3916. Min Range: -2.3916

Max Act: 2.2236. Min Act: -0.0000

Data Index: 541452 (C4 (Web Text))

Max Activating Token Index: 21

Text #2

Max Range: 2.3916. Min Range: -2.3916

Max Act: 2.0010. Min Act: -0.0000

Data Index: 848855 (C4 (Web Text))

Max Activating Token Index: 877

Text #3

Max Range: 2.3916. Min Range: -2.3916

Max Act: 2.0333. Min Act: -0.0000

Data Index: 1044718 (C4 (Web Text))

Max Activating Token Index: 127

Text #4

Max Range: 2.3916. Min Range: -2.3916

Max Act: 2.1373. Min Act: -0.0000

Data Index: 424677 (C4 (Web Text))

Max Activating Token Index: 1018

Text #5

Max Range: 2.3916. Min Range: -2.3916

Max Act: 2.0905. Min Act: -0.0000

Data Index: 195777 (C4 (Web Text))

Max Activating Token Index: 110

Text #6

Max Range: 2.3916. Min Range: -2.3916

Max Act: 2.0576. Min Act: -0.0000

Data Index: 282312 (C4 (Web Text))

Max Activating Token Index: 72

Text #7

Max Range: 2.3916. Min Range: -2.3916

Max Act: 1.9329. Min Act: 0.0000

Data Index: 75595 (C4 (Web Text))

Max Activating Token Index: 531

Text #8

Max Range: 2.3916. Min Range: -2.3916

Max Act: 1.7809. Min Act: -0.0000

Data Index: 195730 (C4 (Web Text))

Max Activating Token Index: 748

Text #9

Max Range: 2.3916. Min Range: -2.3916

Max Act: 1.8793. Min Act: -0.0000

Data Index: 998965 (C4 (Web Text))

Max Activating Token Index: 783

Text #10

Max Range: 2.3916. Min Range: -2.3916

Max Act: 1.7712. Min Act: -0.0000

Data Index: 1276683 (C4 (Web Text))

Max Activating Token Index: 492

Text #11

Max Range: 2.3916. Min Range: -2.3916

Max Act: 1.7304. Min Act: -0.0000

Data Index: 544397 (C4 (Web Text))

Max Activating Token Index: 715

Text #12

Max Range: 2.3916. Min Range: -2.3916

Max Act: 1.6915. Min Act: -0.0000

Data Index: 1088862 (C4 (Web Text))

Max Activating Token Index: 966

Text #13

Max Range: 2.3916. Min Range: -2.3916

Max Act: 1.6668. Min Act: -0.0000

Data Index: 835702 (C4 (Web Text))

Max Activating Token Index: 879

Text #14

Max Range: 2.3916. Min Range: -2.3916

Max Act: 1.7009. Min Act: -0.0000

Data Index: 327749 (C4 (Web Text))

Max Activating Token Index: 116

Text #15

Max Range: 2.3916. Min Range: -2.3916

Max Act: 1.6285. Min Act: -0.0000

Data Index: 1012124 (C4 (Web Text))

Max Activating Token Index: 672

Text #16

Max Range: 2.3916. Min Range: -2.3916

Max Act: 1.6120. Min Act: -0.0000

Data Index: 1137381 (C4 (Web Text))

Max Activating Token Index: 50

Text #17

Max Range: 2.3916. Min Range: -2.3916

Max Act: 1.5380. Min Act: 0.0000

Data Index: 394180 (C4 (Web Text))

Max Activating Token Index: 136

Text #18

Max Range: 2.3916. Min Range: -2.3916

Max Act: 1.6096. Min Act: -0.0000

Data Index: 1079873 (C4 (Web Text))

Max Activating Token Index: 756

Text #19

Max Range: 2.3916. Min Range: -2.3916

Max Act: 1.5896. Min Act: 0.0000

Data Index: 528147 (C4 (Web Text))

Max Activating Token Index: 726