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

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

Neuron 1469 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: 2.1825. Min Range: -2.1825

Max Act: 1.9068. Min Act: -0.0001

Data Index: 903783 (C4 (Web Text))

Max Activating Token Index: 396

Text #1

Max Range: 2.1825. Min Range: -2.1825

Max Act: 1.8156. Min Act: -0.0000

Data Index: 349613 (C4 (Web Text))

Max Activating Token Index: 790

Text #2

Max Range: 2.1825. Min Range: -2.1825

Max Act: 2.1399. Min Act: -0.0000

Data Index: 1256076 (C4 (Web Text))

Max Activating Token Index: 230

Text #3

Max Range: 2.1825. Min Range: -2.1825

Max Act: 2.1825. Min Act: -0.0001

Data Index: 556198 (C4 (Web Text))

Max Activating Token Index: 209

Text #4

Max Range: 2.1825. Min Range: -2.1825

Max Act: 1.7948. Min Act: -0.0000

Data Index: 1039809 (C4 (Web Text))

Max Activating Token Index: 273

Text #5

Max Range: 2.1825. Min Range: -2.1825

Max Act: 1.7179. Min Act: -0.0000

Data Index: 1001248 (C4 (Web Text))

Max Activating Token Index: 213

Text #6

Max Range: 2.1825. Min Range: -2.1825

Max Act: 1.5766. Min Act: -0.0000

Data Index: 238781 (C4 (Web Text))

Max Activating Token Index: 879

Text #7

Max Range: 2.1825. Min Range: -2.1825

Max Act: 1.9023. Min Act: -0.0000

Data Index: 1353913 (C4 (Web Text))

Max Activating Token Index: 731

Text #8

Max Range: 2.1825. Min Range: -2.1825

Max Act: 1.8634. Min Act: -0.0000

Data Index: 1330301 (C4 (Web Text))

Max Activating Token Index: 46

Text #9

Max Range: 2.1825. Min Range: -2.1825

Max Act: 1.6687. Min Act: -0.0000

Data Index: 1257950 (C4 (Web Text))

Max Activating Token Index: 562

Text #10

Max Range: 2.1825. Min Range: -2.1825

Max Act: 1.5649. Min Act: -0.0000

Data Index: 546761 (C4 (Web Text))

Max Activating Token Index: 623

Text #11

Max Range: 2.1825. Min Range: -2.1825

Max Act: 1.8338. Min Act: -0.0000

Data Index: 488046 (C4 (Web Text))

Max Activating Token Index: 992

Text #12

Max Range: 2.1825. Min Range: -2.1825

Max Act: 1.9451. Min Act: -0.0000

Data Index: 234548 (C4 (Web Text))

Max Activating Token Index: 182

Text #13

Max Range: 2.1825. Min Range: -2.1825

Max Act: 1.8249. Min Act: -0.0000

Data Index: 450805 (C4 (Web Text))

Max Activating Token Index: 747

Text #14

Max Range: 2.1825. Min Range: -2.1825

Max Act: 1.7265. Min Act: -0.0000

Data Index: 212906 (C4 (Web Text))

Max Activating Token Index: 420

Text #15

Max Range: 2.1825. Min Range: -2.1825

Max Act: 1.6948. Min Act: -0.0001

Data Index: 337665 (C4 (Web Text))

Max Activating Token Index: 26

Text #16

Max Range: 2.1825. Min Range: -2.1825

Max Act: 1.7797. Min Act: -0.0000

Data Index: 628086 (C4 (Web Text))

Max Activating Token Index: 415

Text #17

Max Range: 2.1825. Min Range: -2.1825

Max Act: 1.8733. Min Act: -0.0000

Data Index: 697677 (C4 (Web Text))

Max Activating Token Index: 740

Text #18

Max Range: 2.1825. Min Range: -2.1825

Max Act: 1.8514. Min Act: -0.0000

Data Index: 1292906 (C4 (Web Text))

Max Activating Token Index: 270

Text #19

Max Range: 2.1825. Min Range: -2.1825

Max Act: 1.7052. Min Act: -0.0000

Data Index: 380986 (C4 (Web Text))

Max Activating Token Index: 683