Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4513 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.2372. Min Range: -1.2372

Max Act: 1.2372. Min Act: -0.0000

Data Index: 252233 (C4 (Web Text))

Max Activating Token Index: 833

Text #1

Max Range: 1.2372. Min Range: -1.2372

Max Act: 1.0800. Min Act: -0.0000

Data Index: 1137307 (C4 (Web Text))

Max Activating Token Index: 972

Text #2

Max Range: 1.2372. Min Range: -1.2372

Max Act: 1.0711. Min Act: -0.0000

Data Index: 1137237 (C4 (Web Text))

Max Activating Token Index: 1013

Text #3

Max Range: 1.2372. Min Range: -1.2372

Max Act: 1.1303. Min Act: -0.0000

Data Index: 1030524 (C4 (Web Text))

Max Activating Token Index: 945

Text #4

Max Range: 1.2372. Min Range: -1.2372

Max Act: 1.0237. Min Act: -0.0000

Data Index: 1241569 (C4 (Web Text))

Max Activating Token Index: 286

Text #5

Max Range: 1.2372. Min Range: -1.2372

Max Act: 1.0562. Min Act: -0.0000

Data Index: 64841 (C4 (Web Text))

Max Activating Token Index: 975

Text #6

Max Range: 1.2372. Min Range: -1.2372

Max Act: 1.0488. Min Act: -0.0000

Data Index: 548379 (C4 (Web Text))

Max Activating Token Index: 127

Text #7

Max Range: 1.2372. Min Range: -1.2372

Max Act: 1.0725. Min Act: -0.0000

Data Index: 381360 (C4 (Web Text))

Max Activating Token Index: 92

Text #8

Max Range: 1.2372. Min Range: -1.2372

Max Act: 1.0362. Min Act: -0.0000

Data Index: 62898 (C4 (Web Text))

Max Activating Token Index: 921

Text #9

Max Range: 1.2372. Min Range: -1.2372

Max Act: 1.0741. Min Act: -0.0000

Data Index: 1227430 (C4 (Web Text))

Max Activating Token Index: 808

Text #10

Max Range: 1.2372. Min Range: -1.2372

Max Act: 1.0471. Min Act: -0.0000

Data Index: 1115887 (C4 (Web Text))

Max Activating Token Index: 115

Text #11

Max Range: 1.2372. Min Range: -1.2372

Max Act: 1.0061. Min Act: -0.0000

Data Index: 163406 (C4 (Web Text))

Max Activating Token Index: 80

Text #12

Max Range: 1.2372. Min Range: -1.2372

Max Act: 1.0746. Min Act: -0.0000

Data Index: 1239173 (C4 (Web Text))

Max Activating Token Index: 565

Text #13

Max Range: 1.2372. Min Range: -1.2372

Max Act: 1.0403. Min Act: -0.0000

Data Index: 1322595 (C4 (Web Text))

Max Activating Token Index: 334

Text #14

Max Range: 1.2372. Min Range: -1.2372

Max Act: 0.9979. Min Act: -0.0000

Data Index: 866745 (C4 (Web Text))

Max Activating Token Index: 924

Text #15

Max Range: 1.2372. Min Range: -1.2372

Max Act: 1.0324. Min Act: -0.0000

Data Index: 1206535 (C4 (Web Text))

Max Activating Token Index: 934

Text #16

Max Range: 1.2372. Min Range: -1.2372

Max Act: 1.0489. Min Act: -0.0000

Data Index: 190167 (C4 (Web Text))

Max Activating Token Index: 536

Text #17

Max Range: 1.2372. Min Range: -1.2372

Max Act: 0.9988. Min Act: -0.0000

Data Index: 1338378 (C4 (Web Text))

Max Activating Token Index: 100

Text #18

Max Range: 1.2372. Min Range: -1.2372

Max Act: 0.9687. Min Act: -0.0000

Data Index: 419325 (C4 (Web Text))

Max Activating Token Index: 597

Text #19

Max Range: 1.2372. Min Range: -1.2372

Max Act: 0.9954. Min Act: -0.0000

Data Index: 1014054 (C4 (Web Text))

Max Activating Token Index: 41