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

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

Neuron 1961 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8418. Min Range: -0.8418

Max Act: 0.8418. Min Act: -0.0001

Data Index: 1105701 (C4 (Web Text))

Max Activating Token Index: 846

Text #1

Max Range: 0.8418. Min Range: -0.8418

Max Act: 0.7076. Min Act: -0.0000

Data Index: 513554 (C4 (Web Text))

Max Activating Token Index: 109

Text #2

Max Range: 0.8418. Min Range: -0.8418

Max Act: 0.7318. Min Act: -0.0001

Data Index: 521578 (C4 (Web Text))

Max Activating Token Index: 734

Text #3

Max Range: 0.8418. Min Range: -0.8418

Max Act: 0.6883. Min Act: -0.0001

Data Index: 374734 (C4 (Web Text))

Max Activating Token Index: 721

Text #4

Max Range: 0.8418. Min Range: -0.8418

Max Act: 0.7536. Min Act: -0.0001

Data Index: 918569 (C4 (Web Text))

Max Activating Token Index: 831

Text #5

Max Range: 0.8418. Min Range: -0.8418

Max Act: 0.6454. Min Act: -0.0001

Data Index: 378086 (C4 (Web Text))

Max Activating Token Index: 296

Text #6

Max Range: 0.8418. Min Range: -0.8418

Max Act: 0.7070. Min Act: -0.0001

Data Index: 637246 (C4 (Web Text))

Max Activating Token Index: 717

Text #7

Max Range: 0.8418. Min Range: -0.8418

Max Act: 0.6157. Min Act: -0.0000

Data Index: 720011 (C4 (Web Text))

Max Activating Token Index: 841

Text #8

Max Range: 0.8418. Min Range: -0.8418

Max Act: 0.6304. Min Act: -0.0001

Data Index: 354563 (C4 (Web Text))

Max Activating Token Index: 319

Text #9

Max Range: 0.8418. Min Range: -0.8418

Max Act: 0.6762. Min Act: -0.0001

Data Index: 698589 (C4 (Web Text))

Max Activating Token Index: 180

Text #10

Max Range: 0.8418. Min Range: -0.8418

Max Act: 0.6456. Min Act: -0.0001

Data Index: 651998 (C4 (Web Text))

Max Activating Token Index: 351

Text #11

Max Range: 0.8418. Min Range: -0.8418

Max Act: 0.6463. Min Act: -0.0001

Data Index: 533856 (C4 (Web Text))

Max Activating Token Index: 670

Text #12

Max Range: 0.8418. Min Range: -0.8418

Max Act: 0.7067. Min Act: -0.0000

Data Index: 620266 (C4 (Web Text))

Max Activating Token Index: 218

Text #13

Max Range: 0.8418. Min Range: -0.8418

Max Act: 0.6147. Min Act: -0.0000

Data Index: 714794 (C4 (Web Text))

Max Activating Token Index: 791

Text #14

Max Range: 0.8418. Min Range: -0.8418

Max Act: 0.6239. Min Act: -0.0001

Data Index: 345447 (C4 (Web Text))

Max Activating Token Index: 604

Text #15

Max Range: 0.8418. Min Range: -0.8418

Max Act: 0.5493. Min Act: -0.0001

Data Index: 1049588 (C4 (Web Text))

Max Activating Token Index: 696

Text #16

Max Range: 0.8418. Min Range: -0.8418

Max Act: 0.5822. Min Act: -0.0001

Data Index: 977376 (C4 (Web Text))

Max Activating Token Index: 498

Text #17

Max Range: 0.8418. Min Range: -0.8418

Max Act: 0.5402. Min Act: -0.0001

Data Index: 1037762 (C4 (Web Text))

Max Activating Token Index: 751

Text #18

Max Range: 0.8418. Min Range: -0.8418

Max Act: 0.6116. Min Act: -0.0001

Data Index: 1061232 (C4 (Web Text))

Max Activating Token Index: 433

Text #19

Max Range: 0.8418. Min Range: -0.8418

Max Act: 0.6102. Min Act: -0.0001

Data Index: 769452 (C4 (Web Text))

Max Activating Token Index: 547