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

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

Neuron 2600 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: 4.0243. Min Range: -4.0243

Max Act: 4.0243. Min Act: -0.0000

Data Index: 284842 (C4 (Web Text))

Max Activating Token Index: 337

Text #1

Max Range: 4.0243. Min Range: -4.0243

Max Act: 2.8775. Min Act: -0.0000

Data Index: 215644 (C4 (Web Text))

Max Activating Token Index: 873

Text #2

Max Range: 4.0243. Min Range: -4.0243

Max Act: 2.8107. Min Act: -0.0000

Data Index: 468939 (C4 (Web Text))

Max Activating Token Index: 644

Text #3

Max Range: 4.0243. Min Range: -4.0243

Max Act: 2.6639. Min Act: -0.0000

Data Index: 33027 (C4 (Web Text))

Max Activating Token Index: 149

Text #4

Max Range: 4.0243. Min Range: -4.0243

Max Act: 2.3009. Min Act: -0.0000

Data Index: 594961 (C4 (Web Text))

Max Activating Token Index: 941

Text #5

Max Range: 4.0243. Min Range: -4.0243

Max Act: 2.4210. Min Act: -0.0000

Data Index: 939026 (C4 (Web Text))

Max Activating Token Index: 259

Text #6

Max Range: 4.0243. Min Range: -4.0243

Max Act: 2.5300. Min Act: -0.0000

Data Index: 58665 (C4 (Web Text))

Max Activating Token Index: 127

Text #7

Max Range: 4.0243. Min Range: -4.0243

Max Act: 2.4155. Min Act: -0.0000

Data Index: 159092 (C4 (Web Text))

Max Activating Token Index: 244

Text #8

Max Range: 4.0243. Min Range: -4.0243

Max Act: 2.2902. Min Act: -0.0000

Data Index: 1115059 (C4 (Web Text))

Max Activating Token Index: 789

Text #9

Max Range: 4.0243. Min Range: -4.0243

Max Act: 2.2178. Min Act: -0.0000

Data Index: 861798 (C4 (Web Text))

Max Activating Token Index: 905

Text #10

Max Range: 4.0243. Min Range: -4.0243

Max Act: 2.3718. Min Act: -0.0000

Data Index: 17485 (C4 (Web Text))

Max Activating Token Index: 563

Text #11

Max Range: 4.0243. Min Range: -4.0243

Max Act: 2.0697. Min Act: -0.0000

Data Index: 939366 (C4 (Web Text))

Max Activating Token Index: 14

Text #12

Max Range: 4.0243. Min Range: -4.0243

Max Act: 2.0507. Min Act: -0.0000

Data Index: 546769 (C4 (Web Text))

Max Activating Token Index: 68

Text #13

Max Range: 4.0243. Min Range: -4.0243

Max Act: 2.1717. Min Act: -0.0000

Data Index: 1441808 (Python Code)

Max Activating Token Index: 233

Text #14

Max Range: 4.0243. Min Range: -4.0243

Max Act: 2.2856. Min Act: -0.0000

Data Index: 940028 (C4 (Web Text))

Max Activating Token Index: 796

Text #15

Max Range: 4.0243. Min Range: -4.0243

Max Act: 2.1527. Min Act: -0.0000

Data Index: 829537 (C4 (Web Text))

Max Activating Token Index: 696

Text #16

Max Range: 4.0243. Min Range: -4.0243

Max Act: 2.1307. Min Act: -0.0000

Data Index: 349220 (C4 (Web Text))

Max Activating Token Index: 499

Text #17

Max Range: 4.0243. Min Range: -4.0243

Max Act: 2.1234. Min Act: -0.0000

Data Index: 1143556 (C4 (Web Text))

Max Activating Token Index: 12

Text #18

Max Range: 4.0243. Min Range: -4.0243

Max Act: 2.2013. Min Act: -0.0000

Data Index: 237283 (C4 (Web Text))

Max Activating Token Index: 654

Text #19

Max Range: 4.0243. Min Range: -4.0243

Max Act: 2.0436. Min Act: -0.0000

Data Index: 440808 (C4 (Web Text))

Max Activating Token Index: 645