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

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

Neuron 3030 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1850. Min Range: -1.1850

Max Act: 1.1850. Min Act: -0.0000

Data Index: 1625057 (Python Code)

Max Activating Token Index: 614

Text #1

Max Range: 1.1850. Min Range: -1.1850

Max Act: 1.1829. Min Act: -0.0000

Data Index: 980964 (C4 (Web Text))

Max Activating Token Index: 12

Text #2

Max Range: 1.1850. Min Range: -1.1850

Max Act: 1.0513. Min Act: -0.0000

Data Index: 303408 (C4 (Web Text))

Max Activating Token Index: 127

Text #3

Max Range: 1.1850. Min Range: -1.1850

Max Act: 1.0615. Min Act: -0.0000

Data Index: 1056176 (C4 (Web Text))

Max Activating Token Index: 357

Text #4

Max Range: 1.1850. Min Range: -1.1850

Max Act: 1.0041. Min Act: -0.0000

Data Index: 458832 (C4 (Web Text))

Max Activating Token Index: 576

Text #5

Max Range: 1.1850. Min Range: -1.1850

Max Act: 0.9609. Min Act: -0.0000

Data Index: 331315 (C4 (Web Text))

Max Activating Token Index: 1008

Text #6

Max Range: 1.1850. Min Range: -1.1850

Max Act: 0.9816. Min Act: -0.0000

Data Index: 1005132 (C4 (Web Text))

Max Activating Token Index: 106

Text #7

Max Range: 1.1850. Min Range: -1.1850

Max Act: 0.9484. Min Act: -0.0000

Data Index: 994386 (C4 (Web Text))

Max Activating Token Index: 975

Text #8

Max Range: 1.1850. Min Range: -1.1850

Max Act: 0.9462. Min Act: -0.0000

Data Index: 869412 (C4 (Web Text))

Max Activating Token Index: 452

Text #9

Max Range: 1.1850. Min Range: -1.1850

Max Act: 0.9521. Min Act: -0.0000

Data Index: 1087653 (C4 (Web Text))

Max Activating Token Index: 34

Text #10

Max Range: 1.1850. Min Range: -1.1850

Max Act: 0.9736. Min Act: -0.0000

Data Index: 624196 (C4 (Web Text))

Max Activating Token Index: 20

Text #11

Max Range: 1.1850. Min Range: -1.1850

Max Act: 0.9411. Min Act: -0.0000

Data Index: 525348 (C4 (Web Text))

Max Activating Token Index: 404

Text #12

Max Range: 1.1850. Min Range: -1.1850

Max Act: 0.9552. Min Act: -0.0000

Data Index: 551036 (C4 (Web Text))

Max Activating Token Index: 12

Text #13

Max Range: 1.1850. Min Range: -1.1850

Max Act: 0.9481. Min Act: -0.0000

Data Index: 802127 (C4 (Web Text))

Max Activating Token Index: 718

Text #14

Max Range: 1.1850. Min Range: -1.1850

Max Act: 0.9075. Min Act: -0.0000

Data Index: 228918 (C4 (Web Text))

Max Activating Token Index: 320

Text #15

Max Range: 1.1850. Min Range: -1.1850

Max Act: 0.9058. Min Act: -0.0000

Data Index: 396923 (C4 (Web Text))

Max Activating Token Index: 320

Text #16

Max Range: 1.1850. Min Range: -1.1850

Max Act: 0.8730. Min Act: -0.0000

Data Index: 494344 (C4 (Web Text))

Max Activating Token Index: 819

Text #17

Max Range: 1.1850. Min Range: -1.1850

Max Act: 0.8979. Min Act: -0.0000

Data Index: 3789 (C4 (Web Text))

Max Activating Token Index: 709

Text #18

Max Range: 1.1850. Min Range: -1.1850

Max Act: 0.8926. Min Act: -0.0000

Data Index: 792719 (C4 (Web Text))

Max Activating Token Index: 55

Text #19

Max Range: 1.1850. Min Range: -1.1850

Max Act: 0.8399. Min Act: -0.0000

Data Index: 1020625 (C4 (Web Text))

Max Activating Token Index: 183