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

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

Neuron 381 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: 4.9318. Min Range: -4.9318

Max Act: 4.9318. Min Act: -0.0000

Data Index: 1100344 (C4 (Web Text))

Max Activating Token Index: 673

Text #1

Max Range: 4.9318. Min Range: -4.9318

Max Act: 4.5254. Min Act: -0.0000

Data Index: 889493 (C4 (Web Text))

Max Activating Token Index: 276

Text #2

Max Range: 4.9318. Min Range: -4.9318

Max Act: 4.2945. Min Act: -0.0000

Data Index: 1212144 (C4 (Web Text))

Max Activating Token Index: 804

Text #3

Max Range: 4.9318. Min Range: -4.9318

Max Act: 4.3574. Min Act: -0.0000

Data Index: 868293 (C4 (Web Text))

Max Activating Token Index: 319

Text #4

Max Range: 4.9318. Min Range: -4.9318

Max Act: 4.6718. Min Act: -0.0000

Data Index: 557833 (C4 (Web Text))

Max Activating Token Index: 930

Text #5

Max Range: 4.9318. Min Range: -4.9318

Max Act: 4.3308. Min Act: -0.0000

Data Index: 240350 (C4 (Web Text))

Max Activating Token Index: 1006

Text #6

Max Range: 4.9318. Min Range: -4.9318

Max Act: 3.9169. Min Act: -0.0000

Data Index: 484776 (C4 (Web Text))

Max Activating Token Index: 508

Text #7

Max Range: 4.9318. Min Range: -4.9318

Max Act: 3.9135. Min Act: -0.0000

Data Index: 906886 (C4 (Web Text))

Max Activating Token Index: 640

Text #8

Max Range: 4.9318. Min Range: -4.9318

Max Act: 3.7235. Min Act: -0.0000

Data Index: 1083000 (C4 (Web Text))

Max Activating Token Index: 850

Text #9

Max Range: 4.9318. Min Range: -4.9318

Max Act: 3.6662. Min Act: -0.0000

Data Index: 724637 (C4 (Web Text))

Max Activating Token Index: 84

Text #10

Max Range: 4.9318. Min Range: -4.9318

Max Act: 3.6606. Min Act: -0.0000

Data Index: 956642 (C4 (Web Text))

Max Activating Token Index: 109

Text #11

Max Range: 4.9318. Min Range: -4.9318

Max Act: 3.8118. Min Act: -0.0000

Data Index: 1402565 (Python Code)

Max Activating Token Index: 856

Text #12

Max Range: 4.9318. Min Range: -4.9318

Max Act: 3.2010. Min Act: -0.0000

Data Index: 936212 (C4 (Web Text))

Max Activating Token Index: 349

Text #13

Max Range: 4.9318. Min Range: -4.9318

Max Act: 3.6145. Min Act: -0.0000

Data Index: 931622 (C4 (Web Text))

Max Activating Token Index: 538

Text #14

Max Range: 4.9318. Min Range: -4.9318

Max Act: 3.1244. Min Act: -0.0000

Data Index: 963901 (C4 (Web Text))

Max Activating Token Index: 248

Text #15

Max Range: 4.9318. Min Range: -4.9318

Max Act: 3.7619. Min Act: -0.0000

Data Index: 913635 (C4 (Web Text))

Max Activating Token Index: 837

Text #16

Max Range: 4.9318. Min Range: -4.9318

Max Act: 3.2305. Min Act: -0.0000

Data Index: 300119 (C4 (Web Text))

Max Activating Token Index: 747

Text #17

Max Range: 4.9318. Min Range: -4.9318

Max Act: 2.8947. Min Act: -0.0000

Data Index: 1248304 (C4 (Web Text))

Max Activating Token Index: 516

Text #18

Max Range: 4.9318. Min Range: -4.9318

Max Act: 3.2192. Min Act: -0.0000

Data Index: 696727 (C4 (Web Text))

Max Activating Token Index: 149

Text #19

Max Range: 4.9318. Min Range: -4.9318

Max Act: 2.9305. Min Act: -0.0000

Data Index: 550195 (C4 (Web Text))

Max Activating Token Index: 224