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

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

Neuron 3439 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9881. Min Range: -0.9881

Max Act: 0.9881. Min Act: -0.0000

Data Index: 1279986 (C4 (Web Text))

Max Activating Token Index: 642

Text #1

Max Range: 0.9881. Min Range: -0.9881

Max Act: 0.9609. Min Act: -0.0000

Data Index: 1092500 (C4 (Web Text))

Max Activating Token Index: 446

Text #2

Max Range: 0.9881. Min Range: -0.9881

Max Act: 0.9037. Min Act: -0.0001

Data Index: 783695 (C4 (Web Text))

Max Activating Token Index: 586

Text #3

Max Range: 0.9881. Min Range: -0.9881

Max Act: 0.8043. Min Act: -0.0001

Data Index: 606242 (C4 (Web Text))

Max Activating Token Index: 332

Text #4

Max Range: 0.9881. Min Range: -0.9881

Max Act: 0.8190. Min Act: -0.0001

Data Index: 707172 (C4 (Web Text))

Max Activating Token Index: 105

Text #5

Max Range: 0.9881. Min Range: -0.9881

Max Act: 0.7573. Min Act: -0.0000

Data Index: 565482 (C4 (Web Text))

Max Activating Token Index: 761

Text #6

Max Range: 0.9881. Min Range: -0.9881

Max Act: 0.7463. Min Act: -0.0000

Data Index: 678726 (C4 (Web Text))

Max Activating Token Index: 62

Text #7

Max Range: 0.9881. Min Range: -0.9881

Max Act: 0.7317. Min Act: -0.0001

Data Index: 811157 (C4 (Web Text))

Max Activating Token Index: 952

Text #8

Max Range: 0.9881. Min Range: -0.9881

Max Act: 0.7488. Min Act: -0.0001

Data Index: 1293543 (C4 (Web Text))

Max Activating Token Index: 426

Text #9

Max Range: 0.9881. Min Range: -0.9881

Max Act: 0.7128. Min Act: -0.0000

Data Index: 938432 (C4 (Web Text))

Max Activating Token Index: 84

Text #10

Max Range: 0.9881. Min Range: -0.9881

Max Act: 0.7022. Min Act: -0.0000

Data Index: 590084 (C4 (Web Text))

Max Activating Token Index: 481

Text #11

Max Range: 0.9881. Min Range: -0.9881

Max Act: 0.6523. Min Act: -0.0001

Data Index: 346402 (C4 (Web Text))

Max Activating Token Index: 325

Text #12

Max Range: 0.9881. Min Range: -0.9881

Max Act: 0.6752. Min Act: -0.0000

Data Index: 162895 (C4 (Web Text))

Max Activating Token Index: 194

Text #13

Max Range: 0.9881. Min Range: -0.9881

Max Act: 0.6618. Min Act: -0.0001

Data Index: 434679 (C4 (Web Text))

Max Activating Token Index: 976

Text #14

Max Range: 0.9881. Min Range: -0.9881

Max Act: 0.6667. Min Act: -0.0000

Data Index: 69653 (C4 (Web Text))

Max Activating Token Index: 524

Text #15

Max Range: 0.9881. Min Range: -0.9881

Max Act: 0.6404. Min Act: -0.0001

Data Index: 486247 (C4 (Web Text))

Max Activating Token Index: 988

Text #16

Max Range: 0.9881. Min Range: -0.9881

Max Act: 0.6551. Min Act: -0.0001

Data Index: 1327004 (C4 (Web Text))

Max Activating Token Index: 420

Text #17

Max Range: 0.9881. Min Range: -0.9881

Max Act: 0.6324. Min Act: -0.0001

Data Index: 127159 (C4 (Web Text))

Max Activating Token Index: 885

Text #18

Max Range: 0.9881. Min Range: -0.9881

Max Act: 0.6103. Min Act: -0.0000

Data Index: 755906 (C4 (Web Text))

Max Activating Token Index: 202

Text #19

Max Range: 0.9881. Min Range: -0.9881

Max Act: 0.6324. Min Act: -0.0000

Data Index: 547223 (C4 (Web Text))

Max Activating Token Index: 841