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

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

Neuron 1880 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.1685. Min Range: -6.1685

Max Act: 6.1685. Min Act: -0.0000

Data Index: 1202551 (C4 (Web Text))

Max Activating Token Index: 1005

Text #1

Max Range: 6.1685. Min Range: -6.1685

Max Act: 5.4390. Min Act: -0.0001

Data Index: 444364 (C4 (Web Text))

Max Activating Token Index: 206

Text #2

Max Range: 6.1685. Min Range: -6.1685

Max Act: 5.2340. Min Act: -0.0001

Data Index: 149211 (C4 (Web Text))

Max Activating Token Index: 860

Text #3

Max Range: 6.1685. Min Range: -6.1685

Max Act: 5.4940. Min Act: -0.0000

Data Index: 1122210 (C4 (Web Text))

Max Activating Token Index: 873

Text #4

Max Range: 6.1685. Min Range: -6.1685

Max Act: 4.9014. Min Act: -0.0000

Data Index: 992196 (C4 (Web Text))

Max Activating Token Index: 719

Text #5

Max Range: 6.1685. Min Range: -6.1685

Max Act: 4.9483. Min Act: -0.0000

Data Index: 1036505 (C4 (Web Text))

Max Activating Token Index: 544

Text #6

Max Range: 6.1685. Min Range: -6.1685

Max Act: 4.7884. Min Act: -0.0000

Data Index: 1252727 (C4 (Web Text))

Max Activating Token Index: 212

Text #7

Max Range: 6.1685. Min Range: -6.1685

Max Act: 5.1171. Min Act: -0.0001

Data Index: 610992 (C4 (Web Text))

Max Activating Token Index: 1005

Text #8

Max Range: 6.1685. Min Range: -6.1685

Max Act: 4.5001. Min Act: -0.0000

Data Index: 724346 (C4 (Web Text))

Max Activating Token Index: 490

Text #9

Max Range: 6.1685. Min Range: -6.1685

Max Act: 4.6351. Min Act: -0.0000

Data Index: 427642 (C4 (Web Text))

Max Activating Token Index: 850

Text #10

Max Range: 6.1685. Min Range: -6.1685

Max Act: 4.6397. Min Act: -0.0000

Data Index: 623883 (C4 (Web Text))

Max Activating Token Index: 9

Text #11

Max Range: 6.1685. Min Range: -6.1685

Max Act: 4.2247. Min Act: -0.0000

Data Index: 1326030 (C4 (Web Text))

Max Activating Token Index: 661

Text #12

Max Range: 6.1685. Min Range: -6.1685

Max Act: 4.3810. Min Act: -0.0000

Data Index: 813526 (C4 (Web Text))

Max Activating Token Index: 585

Text #13

Max Range: 6.1685. Min Range: -6.1685

Max Act: 4.9331. Min Act: -0.0000

Data Index: 871243 (C4 (Web Text))

Max Activating Token Index: 263

Text #14

Max Range: 6.1685. Min Range: -6.1685

Max Act: 3.9053. Min Act: -0.0000

Data Index: 824933 (C4 (Web Text))

Max Activating Token Index: 64

Text #15

Max Range: 6.1685. Min Range: -6.1685

Max Act: 4.0727. Min Act: -0.0000

Data Index: 1036607 (C4 (Web Text))

Max Activating Token Index: 250

Text #16

Max Range: 6.1685. Min Range: -6.1685

Max Act: 4.3664. Min Act: -0.0001

Data Index: 385163 (C4 (Web Text))

Max Activating Token Index: 83

Text #17

Max Range: 6.1685. Min Range: -6.1685

Max Act: 4.6768. Min Act: -0.0000

Data Index: 279237 (C4 (Web Text))

Max Activating Token Index: 918

Text #18

Max Range: 6.1685. Min Range: -6.1685

Max Act: 4.2526. Min Act: -0.0000

Data Index: 132902 (C4 (Web Text))

Max Activating Token Index: 314

Text #19

Max Range: 6.1685. Min Range: -6.1685

Max Act: 3.8610. Min Act: -0.0000

Data Index: 76463 (C4 (Web Text))

Max Activating Token Index: 840