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

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

Neuron 1308 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: 4.9971. Min Range: -4.9971

Max Act: 4.9971. Min Act: -0.0000

Data Index: 1028505 (C4 (Web Text))

Max Activating Token Index: 895

Text #1

Max Range: 4.9971. Min Range: -4.9971

Max Act: 3.0394. Min Act: -0.0000

Data Index: 930649 (C4 (Web Text))

Max Activating Token Index: 437

Text #2

Max Range: 4.9971. Min Range: -4.9971

Max Act: 3.0223. Min Act: -0.0000

Data Index: 190535 (C4 (Web Text))

Max Activating Token Index: 60

Text #3

Max Range: 4.9971. Min Range: -4.9971

Max Act: 2.7600. Min Act: -0.0000

Data Index: 1284495 (C4 (Web Text))

Max Activating Token Index: 455

Text #4

Max Range: 4.9971. Min Range: -4.9971

Max Act: 2.9748. Min Act: 0.0000

Data Index: 126718 (C4 (Web Text))

Max Activating Token Index: 247

Text #5

Max Range: 4.9971. Min Range: -4.9971

Max Act: 2.8364. Min Act: -0.0000

Data Index: 404157 (C4 (Web Text))

Max Activating Token Index: 129

Text #6

Max Range: 4.9971. Min Range: -4.9971

Max Act: 2.7955. Min Act: -0.0000

Data Index: 517305 (C4 (Web Text))

Max Activating Token Index: 191

Text #7

Max Range: 4.9971. Min Range: -4.9971

Max Act: 2.5193. Min Act: -0.0000

Data Index: 42320 (C4 (Web Text))

Max Activating Token Index: 913

Text #8

Max Range: 4.9971. Min Range: -4.9971

Max Act: 2.6616. Min Act: -0.0000

Data Index: 740861 (C4 (Web Text))

Max Activating Token Index: 444

Text #9

Max Range: 4.9971. Min Range: -4.9971

Max Act: 2.8770. Min Act: -0.0000

Data Index: 724327 (C4 (Web Text))

Max Activating Token Index: 651

Text #10

Max Range: 4.9971. Min Range: -4.9971

Max Act: 2.2384. Min Act: -0.0000

Data Index: 672158 (C4 (Web Text))

Max Activating Token Index: 273

Text #11

Max Range: 4.9971. Min Range: -4.9971

Max Act: 2.4586. Min Act: -0.0000

Data Index: 532085 (C4 (Web Text))

Max Activating Token Index: 470

Text #12

Max Range: 4.9971. Min Range: -4.9971

Max Act: 2.4329. Min Act: -0.0000

Data Index: 1015430 (C4 (Web Text))

Max Activating Token Index: 357

Text #13

Max Range: 4.9971. Min Range: -4.9971

Max Act: 2.3887. Min Act: -0.0000

Data Index: 998467 (C4 (Web Text))

Max Activating Token Index: 709

Text #14

Max Range: 4.9971. Min Range: -4.9971

Max Act: 2.3911. Min Act: -0.0000

Data Index: 1277299 (C4 (Web Text))

Max Activating Token Index: 690

Text #15

Max Range: 4.9971. Min Range: -4.9971

Max Act: 2.3275. Min Act: -0.0000

Data Index: 1274719 (C4 (Web Text))

Max Activating Token Index: 749

Text #16

Max Range: 4.9971. Min Range: -4.9971

Max Act: 2.4389. Min Act: -0.0000

Data Index: 1029497 (C4 (Web Text))

Max Activating Token Index: 707

Text #17

Max Range: 4.9971. Min Range: -4.9971

Max Act: 2.0710. Min Act: -0.0000

Data Index: 228082 (C4 (Web Text))

Max Activating Token Index: 612

Text #18

Max Range: 4.9971. Min Range: -4.9971

Max Act: 2.2680. Min Act: -0.0000

Data Index: 377464 (C4 (Web Text))

Max Activating Token Index: 319

Text #19

Max Range: 4.9971. Min Range: -4.9971

Max Act: 2.1629. Min Act: -0.0000

Data Index: 985901 (C4 (Web Text))

Max Activating Token Index: 674