Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2596 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.0030. Min Range: -1.0030

Max Act: 1.0030. Min Act: -0.0001

Data Index: 253678 (C4 (Web Text))

Max Activating Token Index: 135

Text #1

Max Range: 1.0030. Min Range: -1.0030

Max Act: 0.9131. Min Act: -0.0001

Data Index: 991569 (C4 (Web Text))

Max Activating Token Index: 219

Text #2

Max Range: 1.0030. Min Range: -1.0030

Max Act: 0.8244. Min Act: -0.0001

Data Index: 606540 (C4 (Web Text))

Max Activating Token Index: 487

Text #3

Max Range: 1.0030. Min Range: -1.0030

Max Act: 0.8196. Min Act: -0.0001

Data Index: 1080718 (C4 (Web Text))

Max Activating Token Index: 126

Text #4

Max Range: 1.0030. Min Range: -1.0030

Max Act: 0.7759. Min Act: -0.0001

Data Index: 873808 (C4 (Web Text))

Max Activating Token Index: 683

Text #5

Max Range: 1.0030. Min Range: -1.0030

Max Act: 0.7476. Min Act: -0.0001

Data Index: 806490 (C4 (Web Text))

Max Activating Token Index: 650

Text #6

Max Range: 1.0030. Min Range: -1.0030

Max Act: 0.7330. Min Act: -0.0001

Data Index: 4776 (C4 (Web Text))

Max Activating Token Index: 808

Text #7

Max Range: 1.0030. Min Range: -1.0030

Max Act: 0.7784. Min Act: -0.0001

Data Index: 101111 (C4 (Web Text))

Max Activating Token Index: 952

Text #8

Max Range: 1.0030. Min Range: -1.0030

Max Act: 0.7357. Min Act: -0.0001

Data Index: 218388 (C4 (Web Text))

Max Activating Token Index: 102

Text #9

Max Range: 1.0030. Min Range: -1.0030

Max Act: 0.6755. Min Act: -0.0001

Data Index: 685679 (C4 (Web Text))

Max Activating Token Index: 134

Text #10

Max Range: 1.0030. Min Range: -1.0030

Max Act: 0.6496. Min Act: -0.0001

Data Index: 442578 (C4 (Web Text))

Max Activating Token Index: 304

Text #11

Max Range: 1.0030. Min Range: -1.0030

Max Act: 0.6612. Min Act: -0.0001

Data Index: 360915 (C4 (Web Text))

Max Activating Token Index: 349

Text #12

Max Range: 1.0030. Min Range: -1.0030

Max Act: 0.6763. Min Act: -0.0001

Data Index: 285446 (C4 (Web Text))

Max Activating Token Index: 999

Text #13

Max Range: 1.0030. Min Range: -1.0030

Max Act: 0.6760. Min Act: -0.0001

Data Index: 767825 (C4 (Web Text))

Max Activating Token Index: 922

Text #14

Max Range: 1.0030. Min Range: -1.0030

Max Act: 0.6924. Min Act: -0.0001

Data Index: 700470 (C4 (Web Text))

Max Activating Token Index: 2

Text #15

Max Range: 1.0030. Min Range: -1.0030

Max Act: 0.6647. Min Act: -0.0001

Data Index: 1217555 (C4 (Web Text))

Max Activating Token Index: 828

Text #16

Max Range: 1.0030. Min Range: -1.0030

Max Act: 0.6884. Min Act: -0.0001

Data Index: 290261 (C4 (Web Text))

Max Activating Token Index: 184

Text #17

Max Range: 1.0030. Min Range: -1.0030

Max Act: 0.6883. Min Act: -0.0001

Data Index: 216782 (C4 (Web Text))

Max Activating Token Index: 496

Text #18

Max Range: 1.0030. Min Range: -1.0030

Max Act: 0.6526. Min Act: -0.0001

Data Index: 417628 (C4 (Web Text))

Max Activating Token Index: 585

Text #19

Max Range: 1.0030. Min Range: -1.0030

Max Act: 0.6538. Min Act: -0.0001

Data Index: 1249846 (C4 (Web Text))

Max Activating Token Index: 922