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

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

Neuron 5544 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.0788. Min Range: -4.0788

Max Act: 4.0788. Min Act: -0.0000

Data Index: 1353695 (C4 (Web Text))

Max Activating Token Index: 630

Text #1

Max Range: 4.0788. Min Range: -4.0788

Max Act: 3.9707. Min Act: -0.0000

Data Index: 602216 (C4 (Web Text))

Max Activating Token Index: 905

Text #2

Max Range: 4.0788. Min Range: -4.0788

Max Act: 3.9838. Min Act: -0.0000

Data Index: 1046665 (C4 (Web Text))

Max Activating Token Index: 923

Text #3

Max Range: 4.0788. Min Range: -4.0788

Max Act: 3.2807. Min Act: -0.0000

Data Index: 18820 (C4 (Web Text))

Max Activating Token Index: 938

Text #4

Max Range: 4.0788. Min Range: -4.0788

Max Act: 3.1591. Min Act: -0.0000

Data Index: 682340 (C4 (Web Text))

Max Activating Token Index: 850

Text #5

Max Range: 4.0788. Min Range: -4.0788

Max Act: 3.0451. Min Act: -0.0000

Data Index: 726321 (C4 (Web Text))

Max Activating Token Index: 600

Text #6

Max Range: 4.0788. Min Range: -4.0788

Max Act: 3.0287. Min Act: -0.0000

Data Index: 156059 (C4 (Web Text))

Max Activating Token Index: 765

Text #7

Max Range: 4.0788. Min Range: -4.0788

Max Act: 3.3015. Min Act: -0.0000

Data Index: 245324 (C4 (Web Text))

Max Activating Token Index: 708

Text #8

Max Range: 4.0788. Min Range: -4.0788

Max Act: 3.0167. Min Act: -0.0000

Data Index: 1341213 (C4 (Web Text))

Max Activating Token Index: 212

Text #9

Max Range: 4.0788. Min Range: -4.0788

Max Act: 2.9760. Min Act: -0.0000

Data Index: 1358151 (C4 (Web Text))

Max Activating Token Index: 171

Text #10

Max Range: 4.0788. Min Range: -4.0788

Max Act: 2.9579. Min Act: -0.0000

Data Index: 832664 (C4 (Web Text))

Max Activating Token Index: 236

Text #11

Max Range: 4.0788. Min Range: -4.0788

Max Act: 3.1130. Min Act: -0.0000

Data Index: 417752 (C4 (Web Text))

Max Activating Token Index: 745

Text #12

Max Range: 4.0788. Min Range: -4.0788

Max Act: 3.0868. Min Act: -0.0000

Data Index: 95144 (C4 (Web Text))

Max Activating Token Index: 232

Text #13

Max Range: 4.0788. Min Range: -4.0788

Max Act: 3.0843. Min Act: -0.0000

Data Index: 877973 (C4 (Web Text))

Max Activating Token Index: 432

Text #14

Max Range: 4.0788. Min Range: -4.0788

Max Act: 3.0511. Min Act: -0.0000

Data Index: 556366 (C4 (Web Text))

Max Activating Token Index: 203

Text #15

Max Range: 4.0788. Min Range: -4.0788

Max Act: 2.9224. Min Act: -0.0000

Data Index: 757449 (C4 (Web Text))

Max Activating Token Index: 601

Text #16

Max Range: 4.0788. Min Range: -4.0788

Max Act: 2.7942. Min Act: -0.0000

Data Index: 1157565 (C4 (Web Text))

Max Activating Token Index: 695

Text #17

Max Range: 4.0788. Min Range: -4.0788

Max Act: 2.9193. Min Act: -0.0000

Data Index: 194453 (C4 (Web Text))

Max Activating Token Index: 454

Text #18

Max Range: 4.0788. Min Range: -4.0788

Max Act: 2.9213. Min Act: -0.0000

Data Index: 1081685 (C4 (Web Text))

Max Activating Token Index: 871

Text #19

Max Range: 4.0788. Min Range: -4.0788

Max Act: 2.9152. Min Act: -0.0000

Data Index: 236234 (C4 (Web Text))

Max Activating Token Index: 461