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

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

Neuron 1974 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3723. Min Range: -2.3723

Max Act: 2.2715. Min Act: -0.0000

Data Index: 196552 (C4 (Web Text))

Max Activating Token Index: 840

Text #1

Max Range: 2.3723. Min Range: -2.3723

Max Act: 2.3723. Min Act: -0.0000

Data Index: 863317 (C4 (Web Text))

Max Activating Token Index: 297

Text #2

Max Range: 2.3723. Min Range: -2.3723

Max Act: 2.2414. Min Act: -0.0000

Data Index: 279304 (C4 (Web Text))

Max Activating Token Index: 101

Text #3

Max Range: 2.3723. Min Range: -2.3723

Max Act: 2.2395. Min Act: -0.0000

Data Index: 1293922 (C4 (Web Text))

Max Activating Token Index: 433

Text #4

Max Range: 2.3723. Min Range: -2.3723

Max Act: 2.1074. Min Act: -0.0000

Data Index: 1283834 (C4 (Web Text))

Max Activating Token Index: 2

Text #5

Max Range: 2.3723. Min Range: -2.3723

Max Act: 2.2087. Min Act: -0.0000

Data Index: 1287864 (C4 (Web Text))

Max Activating Token Index: 430

Text #6

Max Range: 2.3723. Min Range: -2.3723

Max Act: 2.0349. Min Act: -0.0000

Data Index: 291035 (C4 (Web Text))

Max Activating Token Index: 74

Text #7

Max Range: 2.3723. Min Range: -2.3723

Max Act: 2.1258. Min Act: -0.0000

Data Index: 470696 (C4 (Web Text))

Max Activating Token Index: 875

Text #8

Max Range: 2.3723. Min Range: -2.3723

Max Act: 2.0714. Min Act: -0.0000

Data Index: 992177 (C4 (Web Text))

Max Activating Token Index: 429

Text #9

Max Range: 2.3723. Min Range: -2.3723

Max Act: 1.9777. Min Act: -0.0000

Data Index: 272668 (C4 (Web Text))

Max Activating Token Index: 419

Text #10

Max Range: 2.3723. Min Range: -2.3723

Max Act: 2.0596. Min Act: -0.0000

Data Index: 439331 (C4 (Web Text))

Max Activating Token Index: 176

Text #11

Max Range: 2.3723. Min Range: -2.3723

Max Act: 2.0458. Min Act: -0.0000

Data Index: 1507792 (Python Code)

Max Activating Token Index: 61

Text #12

Max Range: 2.3723. Min Range: -2.3723

Max Act: 1.9062. Min Act: -0.0000

Data Index: 354265 (C4 (Web Text))

Max Activating Token Index: 676

Text #13

Max Range: 2.3723. Min Range: -2.3723

Max Act: 1.9893. Min Act: -0.0000

Data Index: 779326 (C4 (Web Text))

Max Activating Token Index: 439

Text #14

Max Range: 2.3723. Min Range: -2.3723

Max Act: 1.9905. Min Act: -0.0000

Data Index: 764490 (C4 (Web Text))

Max Activating Token Index: 1020

Text #15

Max Range: 2.3723. Min Range: -2.3723

Max Act: 1.8477. Min Act: -0.0000

Data Index: 1241760 (C4 (Web Text))

Max Activating Token Index: 639

Text #16

Max Range: 2.3723. Min Range: -2.3723

Max Act: 1.9501. Min Act: -0.0000

Data Index: 768951 (C4 (Web Text))

Max Activating Token Index: 611

Text #17

Max Range: 2.3723. Min Range: -2.3723

Max Act: 2.0433. Min Act: -0.0000

Data Index: 16620 (C4 (Web Text))

Max Activating Token Index: 144

Text #18

Max Range: 2.3723. Min Range: -2.3723

Max Act: 1.9181. Min Act: -0.0000

Data Index: 1162777 (C4 (Web Text))

Max Activating Token Index: 883

Text #19

Max Range: 2.3723. Min Range: -2.3723

Max Act: 1.9110. Min Act: -0.0000

Data Index: 212447 (C4 (Web Text))

Max Activating Token Index: 582