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

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

Neuron 5551 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: 4.8368. Min Range: -4.8368

Max Act: 4.8368. Min Act: -0.0000

Data Index: 1260525 (C4 (Web Text))

Max Activating Token Index: 808

Text #1

Max Range: 4.8368. Min Range: -4.8368

Max Act: 4.0016. Min Act: -0.0000

Data Index: 142250 (C4 (Web Text))

Max Activating Token Index: 670

Text #2

Max Range: 4.8368. Min Range: -4.8368

Max Act: 4.7923. Min Act: -0.0000

Data Index: 1165156 (C4 (Web Text))

Max Activating Token Index: 244

Text #3

Max Range: 4.8368. Min Range: -4.8368

Max Act: 4.1002. Min Act: -0.0000

Data Index: 805642 (C4 (Web Text))

Max Activating Token Index: 463

Text #4

Max Range: 4.8368. Min Range: -4.8368

Max Act: 3.9280. Min Act: -0.0000

Data Index: 891197 (C4 (Web Text))

Max Activating Token Index: 960

Text #5

Max Range: 4.8368. Min Range: -4.8368

Max Act: 4.1567. Min Act: -0.0000

Data Index: 208539 (C4 (Web Text))

Max Activating Token Index: 223

Text #6

Max Range: 4.8368. Min Range: -4.8368

Max Act: 4.0241. Min Act: -0.0000

Data Index: 1220069 (C4 (Web Text))

Max Activating Token Index: 980

Text #7

Max Range: 4.8368. Min Range: -4.8368

Max Act: 3.9909. Min Act: -0.0000

Data Index: 796177 (C4 (Web Text))

Max Activating Token Index: 234

Text #8

Max Range: 4.8368. Min Range: -4.8368

Max Act: 4.4537. Min Act: -0.0001

Data Index: 922058 (C4 (Web Text))

Max Activating Token Index: 882

Text #9

Max Range: 4.8368. Min Range: -4.8368

Max Act: 4.0410. Min Act: -0.0000

Data Index: 667060 (C4 (Web Text))

Max Activating Token Index: 795

Text #10

Max Range: 4.8368. Min Range: -4.8368

Max Act: 4.3757. Min Act: -0.0001

Data Index: 669816 (C4 (Web Text))

Max Activating Token Index: 488

Text #11

Max Range: 4.8368. Min Range: -4.8368

Max Act: 4.2128. Min Act: -0.0000

Data Index: 694487 (C4 (Web Text))

Max Activating Token Index: 196

Text #12

Max Range: 4.8368. Min Range: -4.8368

Max Act: 3.9392. Min Act: -0.0000

Data Index: 1072850 (C4 (Web Text))

Max Activating Token Index: 137

Text #13

Max Range: 4.8368. Min Range: -4.8368

Max Act: 4.2170. Min Act: -0.0000

Data Index: 913815 (C4 (Web Text))

Max Activating Token Index: 603

Text #14

Max Range: 4.8368. Min Range: -4.8368

Max Act: 3.8819. Min Act: -0.0000

Data Index: 701950 (C4 (Web Text))

Max Activating Token Index: 239

Text #15

Max Range: 4.8368. Min Range: -4.8368

Max Act: 3.9457. Min Act: -0.0000

Data Index: 540694 (C4 (Web Text))

Max Activating Token Index: 143

Text #16

Max Range: 4.8368. Min Range: -4.8368

Max Act: 3.7848. Min Act: -0.0000

Data Index: 603304 (C4 (Web Text))

Max Activating Token Index: 664

Text #17

Max Range: 4.8368. Min Range: -4.8368

Max Act: 4.0151. Min Act: -0.0000

Data Index: 1277406 (C4 (Web Text))

Max Activating Token Index: 623

Text #18

Max Range: 4.8368. Min Range: -4.8368

Max Act: 3.7524. Min Act: -0.0000

Data Index: 205556 (C4 (Web Text))

Max Activating Token Index: 333

Text #19

Max Range: 4.8368. Min Range: -4.8368

Max Act: 3.8897. Min Act: -0.0000

Data Index: 1082973 (C4 (Web Text))

Max Activating Token Index: 244