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

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

Neuron 2953 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1670. Min Range: -1.1670

Max Act: 1.1670. Min Act: -0.0000

Data Index: 749753 (C4 (Web Text))

Max Activating Token Index: 926

Text #1

Max Range: 1.1670. Min Range: -1.1670

Max Act: 1.0457. Min Act: -0.0000

Data Index: 464725 (C4 (Web Text))

Max Activating Token Index: 891

Text #2

Max Range: 1.1670. Min Range: -1.1670

Max Act: 1.0675. Min Act: -0.0000

Data Index: 1001537 (C4 (Web Text))

Max Activating Token Index: 965

Text #3

Max Range: 1.1670. Min Range: -1.1670

Max Act: 1.0692. Min Act: -0.0000

Data Index: 84817 (C4 (Web Text))

Max Activating Token Index: 52

Text #4

Max Range: 1.1670. Min Range: -1.1670

Max Act: 1.1272. Min Act: -0.0000

Data Index: 247166 (C4 (Web Text))

Max Activating Token Index: 972

Text #5

Max Range: 1.1670. Min Range: -1.1670

Max Act: 1.0520. Min Act: -0.0000

Data Index: 462505 (C4 (Web Text))

Max Activating Token Index: 800

Text #6

Max Range: 1.1670. Min Range: -1.1670

Max Act: 1.0704. Min Act: -0.0000

Data Index: 53728 (C4 (Web Text))

Max Activating Token Index: 550

Text #7

Max Range: 1.1670. Min Range: -1.1670

Max Act: 1.0655. Min Act: -0.0000

Data Index: 1298429 (C4 (Web Text))

Max Activating Token Index: 698

Text #8

Max Range: 1.1670. Min Range: -1.1670

Max Act: 1.0599. Min Act: -0.0000

Data Index: 712582 (C4 (Web Text))

Max Activating Token Index: 847

Text #9

Max Range: 1.1670. Min Range: -1.1670

Max Act: 1.0190. Min Act: -0.0000

Data Index: 1284087 (C4 (Web Text))

Max Activating Token Index: 745

Text #10

Max Range: 1.1670. Min Range: -1.1670

Max Act: 1.0181. Min Act: -0.0000

Data Index: 327148 (C4 (Web Text))

Max Activating Token Index: 852

Text #11

Max Range: 1.1670. Min Range: -1.1670

Max Act: 1.0386. Min Act: -0.0000

Data Index: 617060 (C4 (Web Text))

Max Activating Token Index: 775

Text #12

Max Range: 1.1670. Min Range: -1.1670

Max Act: 1.0331. Min Act: -0.0000

Data Index: 954394 (C4 (Web Text))

Max Activating Token Index: 167

Text #13

Max Range: 1.1670. Min Range: -1.1670

Max Act: 0.9292. Min Act: -0.0000

Data Index: 798387 (C4 (Web Text))

Max Activating Token Index: 375

Text #14

Max Range: 1.1670. Min Range: -1.1670

Max Act: 0.9911. Min Act: -0.0000

Data Index: 473045 (C4 (Web Text))

Max Activating Token Index: 360

Text #15

Max Range: 1.1670. Min Range: -1.1670

Max Act: 0.9767. Min Act: -0.0000

Data Index: 1359657 (C4 (Web Text))

Max Activating Token Index: 271

Text #16

Max Range: 1.1670. Min Range: -1.1670

Max Act: 0.9176. Min Act: -0.0000

Data Index: 1254605 (C4 (Web Text))

Max Activating Token Index: 164

Text #17

Max Range: 1.1670. Min Range: -1.1670

Max Act: 0.9575. Min Act: -0.0000

Data Index: 684649 (C4 (Web Text))

Max Activating Token Index: 524

Text #18

Max Range: 1.1670. Min Range: -1.1670

Max Act: 0.9743. Min Act: -0.0000

Data Index: 40405 (C4 (Web Text))

Max Activating Token Index: 410

Text #19

Max Range: 1.1670. Min Range: -1.1670

Max Act: 0.9306. Min Act: -0.0000

Data Index: 1332692 (C4 (Web Text))

Max Activating Token Index: 900