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

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

Neuron 1856 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0337. Min Range: -2.0337

Max Act: 2.0337. Min Act: -0.0000

Data Index: 1195099 (C4 (Web Text))

Max Activating Token Index: 623

Text #1

Max Range: 2.0337. Min Range: -2.0337

Max Act: 1.6730. Min Act: -0.0000

Data Index: 301845 (C4 (Web Text))

Max Activating Token Index: 644

Text #2

Max Range: 2.0337. Min Range: -2.0337

Max Act: 1.6608. Min Act: -0.0000

Data Index: 1074006 (C4 (Web Text))

Max Activating Token Index: 156

Text #3

Max Range: 2.0337. Min Range: -2.0337

Max Act: 1.7440. Min Act: -0.0000

Data Index: 1204521 (C4 (Web Text))

Max Activating Token Index: 656

Text #4

Max Range: 2.0337. Min Range: -2.0337

Max Act: 1.7155. Min Act: -0.0000

Data Index: 289750 (C4 (Web Text))

Max Activating Token Index: 780

Text #5

Max Range: 2.0337. Min Range: -2.0337

Max Act: 1.5721. Min Act: -0.0000

Data Index: 1340954 (C4 (Web Text))

Max Activating Token Index: 168

Text #6

Max Range: 2.0337. Min Range: -2.0337

Max Act: 1.5381. Min Act: -0.0000

Data Index: 305499 (C4 (Web Text))

Max Activating Token Index: 21

Text #7

Max Range: 2.0337. Min Range: -2.0337

Max Act: 1.6217. Min Act: -0.0000

Data Index: 1251202 (C4 (Web Text))

Max Activating Token Index: 792

Text #8

Max Range: 2.0337. Min Range: -2.0337

Max Act: 1.4926. Min Act: -0.0000

Data Index: 57054 (C4 (Web Text))

Max Activating Token Index: 935

Text #9

Max Range: 2.0337. Min Range: -2.0337

Max Act: 1.5083. Min Act: -0.0000

Data Index: 1204781 (C4 (Web Text))

Max Activating Token Index: 821

Text #10

Max Range: 2.0337. Min Range: -2.0337

Max Act: 1.4359. Min Act: -0.0000

Data Index: 378628 (C4 (Web Text))

Max Activating Token Index: 334

Text #11

Max Range: 2.0337. Min Range: -2.0337

Max Act: 1.2785. Min Act: -0.0000

Data Index: 148877 (C4 (Web Text))

Max Activating Token Index: 611

Text #12

Max Range: 2.0337. Min Range: -2.0337

Max Act: 1.2810. Min Act: -0.0000

Data Index: 454686 (C4 (Web Text))

Max Activating Token Index: 483

Text #13

Max Range: 2.0337. Min Range: -2.0337

Max Act: 1.3031. Min Act: -0.0000

Data Index: 1294020 (C4 (Web Text))

Max Activating Token Index: 220

Text #14

Max Range: 2.0337. Min Range: -2.0337

Max Act: 1.3397. Min Act: -0.0000

Data Index: 513005 (C4 (Web Text))

Max Activating Token Index: 9

Text #15

Max Range: 2.0337. Min Range: -2.0337

Max Act: 1.3393. Min Act: -0.0000

Data Index: 1318244 (C4 (Web Text))

Max Activating Token Index: 246

Text #16

Max Range: 2.0337. Min Range: -2.0337

Max Act: 1.1395. Min Act: -0.0000

Data Index: 1142248 (C4 (Web Text))

Max Activating Token Index: 530

Text #17

Max Range: 2.0337. Min Range: -2.0337

Max Act: 1.3789. Min Act: -0.0000

Data Index: 868944 (C4 (Web Text))

Max Activating Token Index: 328

Text #18

Max Range: 2.0337. Min Range: -2.0337

Max Act: 1.2425. Min Act: -0.0000

Data Index: 340899 (C4 (Web Text))

Max Activating Token Index: 381

Text #19

Max Range: 2.0337. Min Range: -2.0337

Max Act: 1.3732. Min Act: -0.0000

Data Index: 890484 (C4 (Web Text))

Max Activating Token Index: 573