Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3386 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 3.6516. Min Range: -3.6516

Max Act: 3.6516. Min Act: -0.0002

Data Index: 226712 (C4 (Web Text))

Max Activating Token Index: 863

Text #1

Max Range: 3.6516. Min Range: -3.6516

Max Act: 3.2595. Min Act: -0.0001

Data Index: 495185 (C4 (Web Text))

Max Activating Token Index: 889

Text #2

Max Range: 3.6516. Min Range: -3.6516

Max Act: 3.1257. Min Act: -0.0001

Data Index: 372906 (C4 (Web Text))

Max Activating Token Index: 697

Text #3

Max Range: 3.6516. Min Range: -3.6516

Max Act: 3.0817. Min Act: -0.0001

Data Index: 252069 (C4 (Web Text))

Max Activating Token Index: 990

Text #4

Max Range: 3.6516. Min Range: -3.6516

Max Act: 3.3452. Min Act: -0.0001

Data Index: 1282856 (C4 (Web Text))

Max Activating Token Index: 605

Text #5

Max Range: 3.6516. Min Range: -3.6516

Max Act: 3.0389. Min Act: -0.0002

Data Index: 39619 (C4 (Web Text))

Max Activating Token Index: 798

Text #6

Max Range: 3.6516. Min Range: -3.6516

Max Act: 2.9798. Min Act: -0.0002

Data Index: 1321967 (C4 (Web Text))

Max Activating Token Index: 349

Text #7

Max Range: 3.6516. Min Range: -3.6516

Max Act: 2.9605. Min Act: -0.0002

Data Index: 246457 (C4 (Web Text))

Max Activating Token Index: 204

Text #8

Max Range: 3.6516. Min Range: -3.6516

Max Act: 3.0302. Min Act: -0.0002

Data Index: 706261 (C4 (Web Text))

Max Activating Token Index: 85

Text #9

Max Range: 3.6516. Min Range: -3.6516

Max Act: 2.9885. Min Act: -0.0001

Data Index: 882919 (C4 (Web Text))

Max Activating Token Index: 594

Text #10

Max Range: 3.6516. Min Range: -3.6516

Max Act: 2.8244. Min Act: -0.0001

Data Index: 212760 (C4 (Web Text))

Max Activating Token Index: 688

Text #11

Max Range: 3.6516. Min Range: -3.6516

Max Act: 2.9737. Min Act: -0.0002

Data Index: 888883 (C4 (Web Text))

Max Activating Token Index: 505

Text #12

Max Range: 3.6516. Min Range: -3.6516

Max Act: 2.8354. Min Act: -0.0001

Data Index: 1141052 (C4 (Web Text))

Max Activating Token Index: 139

Text #13

Max Range: 3.6516. Min Range: -3.6516

Max Act: 2.8340. Min Act: -0.0001

Data Index: 1250610 (C4 (Web Text))

Max Activating Token Index: 834

Text #14

Max Range: 3.6516. Min Range: -3.6516

Max Act: 2.6724. Min Act: -0.0001

Data Index: 1025273 (C4 (Web Text))

Max Activating Token Index: 117

Text #15

Max Range: 3.6516. Min Range: -3.6516

Max Act: 2.7722. Min Act: -0.0001

Data Index: 547057 (C4 (Web Text))

Max Activating Token Index: 386

Text #16

Max Range: 3.6516. Min Range: -3.6516

Max Act: 2.6406. Min Act: -0.0001

Data Index: 756320 (C4 (Web Text))

Max Activating Token Index: 385

Text #17

Max Range: 3.6516. Min Range: -3.6516

Max Act: 2.6975. Min Act: -0.0001

Data Index: 79053 (C4 (Web Text))

Max Activating Token Index: 730

Text #18

Max Range: 3.6516. Min Range: -3.6516

Max Act: 2.4632. Min Act: -0.0001

Data Index: 325533 (C4 (Web Text))

Max Activating Token Index: 90

Text #19

Max Range: 3.6516. Min Range: -3.6516

Max Act: 2.4252. Min Act: -0.0001

Data Index: 436436 (C4 (Web Text))

Max Activating Token Index: 545