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

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

Neuron 4154 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: 1.0664. Min Range: -1.0664

Max Act: 1.0664. Min Act: -0.0000

Data Index: 1342420 (C4 (Web Text))

Max Activating Token Index: 30

Text #1

Max Range: 1.0664. Min Range: -1.0664

Max Act: 0.8521. Min Act: -0.0000

Data Index: 1101655 (C4 (Web Text))

Max Activating Token Index: 160

Text #2

Max Range: 1.0664. Min Range: -1.0664

Max Act: 0.7679. Min Act: -0.0000

Data Index: 813395 (C4 (Web Text))

Max Activating Token Index: 564

Text #3

Max Range: 1.0664. Min Range: -1.0664

Max Act: 0.7196. Min Act: -0.0000

Data Index: 329055 (C4 (Web Text))

Max Activating Token Index: 635

Text #4

Max Range: 1.0664. Min Range: -1.0664

Max Act: 0.7303. Min Act: -0.0000

Data Index: 1232524 (C4 (Web Text))

Max Activating Token Index: 970

Text #5

Max Range: 1.0664. Min Range: -1.0664

Max Act: 0.7303. Min Act: -0.0000

Data Index: 1082743 (C4 (Web Text))

Max Activating Token Index: 981

Text #6

Max Range: 1.0664. Min Range: -1.0664

Max Act: 0.6980. Min Act: -0.0000

Data Index: 28752 (C4 (Web Text))

Max Activating Token Index: 154

Text #7

Max Range: 1.0664. Min Range: -1.0664

Max Act: 0.6657. Min Act: -0.0000

Data Index: 615189 (C4 (Web Text))

Max Activating Token Index: 805

Text #8

Max Range: 1.0664. Min Range: -1.0664

Max Act: 0.6644. Min Act: -0.0000

Data Index: 728387 (C4 (Web Text))

Max Activating Token Index: 90

Text #9

Max Range: 1.0664. Min Range: -1.0664

Max Act: 0.7283. Min Act: -0.0000

Data Index: 988117 (C4 (Web Text))

Max Activating Token Index: 777

Text #10

Max Range: 1.0664. Min Range: -1.0664

Max Act: 0.6922. Min Act: -0.0000

Data Index: 482776 (C4 (Web Text))

Max Activating Token Index: 734

Text #11

Max Range: 1.0664. Min Range: -1.0664

Max Act: 0.6415. Min Act: 0.0000

Data Index: 582701 (C4 (Web Text))

Max Activating Token Index: 163

Text #12

Max Range: 1.0664. Min Range: -1.0664

Max Act: 0.6736. Min Act: -0.0000

Data Index: 822343 (C4 (Web Text))

Max Activating Token Index: 235

Text #13

Max Range: 1.0664. Min Range: -1.0664

Max Act: 0.6411. Min Act: -0.0000

Data Index: 824700 (C4 (Web Text))

Max Activating Token Index: 183

Text #14

Max Range: 1.0664. Min Range: -1.0664

Max Act: 0.6306. Min Act: -0.0000

Data Index: 426682 (C4 (Web Text))

Max Activating Token Index: 1013

Text #15

Max Range: 1.0664. Min Range: -1.0664

Max Act: 0.6169. Min Act: -0.0000

Data Index: 1173188 (C4 (Web Text))

Max Activating Token Index: 62

Text #16

Max Range: 1.0664. Min Range: -1.0664

Max Act: 0.6216. Min Act: 0.0000

Data Index: 257104 (C4 (Web Text))

Max Activating Token Index: 737

Text #17

Max Range: 1.0664. Min Range: -1.0664

Max Act: 0.5635. Min Act: -0.0000

Data Index: 977340 (C4 (Web Text))

Max Activating Token Index: 701

Text #18

Max Range: 1.0664. Min Range: -1.0664

Max Act: 0.6023. Min Act: -0.0000

Data Index: 1154783 (C4 (Web Text))

Max Activating Token Index: 487

Text #19

Max Range: 1.0664. Min Range: -1.0664

Max Act: 0.5905. Min Act: -0.0000

Data Index: 940703 (C4 (Web Text))

Max Activating Token Index: 206