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

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

Neuron 1089 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8365. Min Range: -2.8365

Max Act: 2.8365. Min Act: -0.0000

Data Index: 1314514 (C4 (Web Text))

Max Activating Token Index: 34

Text #1

Max Range: 2.8365. Min Range: -2.8365

Max Act: 2.1116. Min Act: -0.0000

Data Index: 338543 (C4 (Web Text))

Max Activating Token Index: 201

Text #2

Max Range: 2.8365. Min Range: -2.8365

Max Act: 2.1918. Min Act: -0.0000

Data Index: 320868 (C4 (Web Text))

Max Activating Token Index: 585

Text #3

Max Range: 2.8365. Min Range: -2.8365

Max Act: 1.9406. Min Act: -0.0000

Data Index: 634104 (C4 (Web Text))

Max Activating Token Index: 406

Text #4

Max Range: 2.8365. Min Range: -2.8365

Max Act: 2.0088. Min Act: -0.0000

Data Index: 599230 (C4 (Web Text))

Max Activating Token Index: 775

Text #5

Max Range: 2.8365. Min Range: -2.8365

Max Act: 1.8860. Min Act: -0.0000

Data Index: 1136800 (C4 (Web Text))

Max Activating Token Index: 27

Text #6

Max Range: 2.8365. Min Range: -2.8365

Max Act: 1.8681. Min Act: -0.0000

Data Index: 167796 (C4 (Web Text))

Max Activating Token Index: 310

Text #7

Max Range: 2.8365. Min Range: -2.8365

Max Act: 1.8609. Min Act: -0.0000

Data Index: 192942 (C4 (Web Text))

Max Activating Token Index: 821

Text #8

Max Range: 2.8365. Min Range: -2.8365

Max Act: 1.8294. Min Act: -0.0000

Data Index: 625186 (C4 (Web Text))

Max Activating Token Index: 464

Text #9

Max Range: 2.8365. Min Range: -2.8365

Max Act: 1.6875. Min Act: -0.0000

Data Index: 1240205 (C4 (Web Text))

Max Activating Token Index: 191

Text #10

Max Range: 2.8365. Min Range: -2.8365

Max Act: 1.6594. Min Act: -0.0000

Data Index: 471516 (C4 (Web Text))

Max Activating Token Index: 565

Text #11

Max Range: 2.8365. Min Range: -2.8365

Max Act: 1.7289. Min Act: -0.0000

Data Index: 128451 (C4 (Web Text))

Max Activating Token Index: 873

Text #12

Max Range: 2.8365. Min Range: -2.8365

Max Act: 1.7180. Min Act: -0.0000

Data Index: 1175750 (C4 (Web Text))

Max Activating Token Index: 772

Text #13

Max Range: 2.8365. Min Range: -2.8365

Max Act: 1.7161. Min Act: -0.0000

Data Index: 1246583 (C4 (Web Text))

Max Activating Token Index: 158

Text #14

Max Range: 2.8365. Min Range: -2.8365

Max Act: 1.7147. Min Act: -0.0000

Data Index: 488785 (C4 (Web Text))

Max Activating Token Index: 601

Text #15

Max Range: 2.8365. Min Range: -2.8365

Max Act: 1.6895. Min Act: -0.0000

Data Index: 499590 (C4 (Web Text))

Max Activating Token Index: 517

Text #16

Max Range: 2.8365. Min Range: -2.8365

Max Act: 1.6859. Min Act: 0.0000

Data Index: 943532 (C4 (Web Text))

Max Activating Token Index: 13

Text #17

Max Range: 2.8365. Min Range: -2.8365

Max Act: 1.7757. Min Act: -0.0000

Data Index: 953415 (C4 (Web Text))

Max Activating Token Index: 16

Text #18

Max Range: 2.8365. Min Range: -2.8365

Max Act: 1.7667. Min Act: -0.0000

Data Index: 866041 (C4 (Web Text))

Max Activating Token Index: 383

Text #19

Max Range: 2.8365. Min Range: -2.8365

Max Act: 1.7536. Min Act: -0.0000

Data Index: 377487 (C4 (Web Text))

Max Activating Token Index: 501