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

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

Neuron 1326 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5453. Min Range: -1.5453

Max Act: 1.3583. Min Act: -0.0001

Data Index: 1358320 (C4 (Web Text))

Max Activating Token Index: 219

Text #1

Max Range: 1.5453. Min Range: -1.5453

Max Act: 1.5453. Min Act: -0.0001

Data Index: 917100 (C4 (Web Text))

Max Activating Token Index: 208

Text #2

Max Range: 1.5453. Min Range: -1.5453

Max Act: 1.3435. Min Act: -0.0001

Data Index: 52653 (C4 (Web Text))

Max Activating Token Index: 55

Text #3

Max Range: 1.5453. Min Range: -1.5453

Max Act: 1.1244. Min Act: -0.0001

Data Index: 537621 (C4 (Web Text))

Max Activating Token Index: 1015

Text #4

Max Range: 1.5453. Min Range: -1.5453

Max Act: 1.1357. Min Act: -0.0001

Data Index: 186484 (C4 (Web Text))

Max Activating Token Index: 25

Text #5

Max Range: 1.5453. Min Range: -1.5453

Max Act: 0.8772. Min Act: -0.0001

Data Index: 985664 (C4 (Web Text))

Max Activating Token Index: 1021

Text #6

Max Range: 1.5453. Min Range: -1.5453

Max Act: 0.8840. Min Act: -0.0001

Data Index: 36029 (C4 (Web Text))

Max Activating Token Index: 818

Text #7

Max Range: 1.5453. Min Range: -1.5453

Max Act: 0.9412. Min Act: -0.0001

Data Index: 493453 (C4 (Web Text))

Max Activating Token Index: 807

Text #8

Max Range: 1.5453. Min Range: -1.5453

Max Act: 0.9684. Min Act: -0.0001

Data Index: 723388 (C4 (Web Text))

Max Activating Token Index: 574

Text #9

Max Range: 1.5453. Min Range: -1.5453

Max Act: 0.9312. Min Act: -0.0001

Data Index: 86039 (C4 (Web Text))

Max Activating Token Index: 450

Text #10

Max Range: 1.5453. Min Range: -1.5453

Max Act: 0.9514. Min Act: -0.0001

Data Index: 566078 (C4 (Web Text))

Max Activating Token Index: 463

Text #11

Max Range: 1.5453. Min Range: -1.5453

Max Act: 0.9418. Min Act: -0.0001

Data Index: 406925 (C4 (Web Text))

Max Activating Token Index: 264

Text #12

Max Range: 1.5453. Min Range: -1.5453

Max Act: 0.8277. Min Act: -0.0001

Data Index: 214348 (C4 (Web Text))

Max Activating Token Index: 588

Text #13

Max Range: 1.5453. Min Range: -1.5453

Max Act: 0.8470. Min Act: -0.0001

Data Index: 255886 (C4 (Web Text))

Max Activating Token Index: 116

Text #14

Max Range: 1.5453. Min Range: -1.5453

Max Act: 0.8461. Min Act: -0.0001

Data Index: 18214 (C4 (Web Text))

Max Activating Token Index: 300

Text #15

Max Range: 1.5453. Min Range: -1.5453

Max Act: 0.9757. Min Act: -0.0001

Data Index: 187208 (C4 (Web Text))

Max Activating Token Index: 721

Text #16

Max Range: 1.5453. Min Range: -1.5453

Max Act: 0.8848. Min Act: -0.0001

Data Index: 640185 (C4 (Web Text))

Max Activating Token Index: 343

Text #17

Max Range: 1.5453. Min Range: -1.5453

Max Act: 0.8261. Min Act: -0.0001

Data Index: 416777 (C4 (Web Text))

Max Activating Token Index: 109

Text #18

Max Range: 1.5453. Min Range: -1.5453

Max Act: 0.8287. Min Act: -0.0001

Data Index: 1045133 (C4 (Web Text))

Max Activating Token Index: 333

Text #19

Max Range: 1.5453. Min Range: -1.5453

Max Act: 0.8401. Min Act: -0.0001

Data Index: 369477 (C4 (Web Text))

Max Activating Token Index: 247