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

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

Neuron 2915 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: 1.9379. Min Range: -1.9379

Max Act: 1.9379. Min Act: -0.0000

Data Index: 1130887 (C4 (Web Text))

Max Activating Token Index: 996

Text #1

Max Range: 1.9379. Min Range: -1.9379

Max Act: 1.8650. Min Act: -0.0000

Data Index: 749944 (C4 (Web Text))

Max Activating Token Index: 915

Text #2

Max Range: 1.9379. Min Range: -1.9379

Max Act: 1.6872. Min Act: -0.0000

Data Index: 442578 (C4 (Web Text))

Max Activating Token Index: 825

Text #3

Max Range: 1.9379. Min Range: -1.9379

Max Act: 1.7542. Min Act: -0.0000

Data Index: 856710 (C4 (Web Text))

Max Activating Token Index: 1019

Text #4

Max Range: 1.9379. Min Range: -1.9379

Max Act: 1.7647. Min Act: -0.0000

Data Index: 1184782 (C4 (Web Text))

Max Activating Token Index: 734

Text #5

Max Range: 1.9379. Min Range: -1.9379

Max Act: 1.6542. Min Act: -0.0000

Data Index: 1050737 (C4 (Web Text))

Max Activating Token Index: 821

Text #6

Max Range: 1.9379. Min Range: -1.9379

Max Act: 1.6436. Min Act: -0.0000

Data Index: 77277 (C4 (Web Text))

Max Activating Token Index: 641

Text #7

Max Range: 1.9379. Min Range: -1.9379

Max Act: 1.5499. Min Act: -0.0000

Data Index: 1121997 (C4 (Web Text))

Max Activating Token Index: 1003

Text #8

Max Range: 1.9379. Min Range: -1.9379

Max Act: 1.7201. Min Act: -0.0000

Data Index: 293787 (C4 (Web Text))

Max Activating Token Index: 358

Text #9

Max Range: 1.9379. Min Range: -1.9379

Max Act: 1.5359. Min Act: -0.0000

Data Index: 145039 (C4 (Web Text))

Max Activating Token Index: 801

Text #10

Max Range: 1.9379. Min Range: -1.9379

Max Act: 1.4232. Min Act: -0.0000

Data Index: 281630 (C4 (Web Text))

Max Activating Token Index: 706

Text #11

Max Range: 1.9379. Min Range: -1.9379

Max Act: 1.4313. Min Act: -0.0000

Data Index: 361906 (C4 (Web Text))

Max Activating Token Index: 424

Text #12

Max Range: 1.9379. Min Range: -1.9379

Max Act: 1.5043. Min Act: -0.0000

Data Index: 781718 (C4 (Web Text))

Max Activating Token Index: 907

Text #13

Max Range: 1.9379. Min Range: -1.9379

Max Act: 1.5837. Min Act: -0.0000

Data Index: 359711 (C4 (Web Text))

Max Activating Token Index: 888

Text #14

Max Range: 1.9379. Min Range: -1.9379

Max Act: 1.4898. Min Act: -0.0000

Data Index: 1376950 (Python Code)

Max Activating Token Index: 660

Text #15

Max Range: 1.9379. Min Range: -1.9379

Max Act: 1.5515. Min Act: -0.0000

Data Index: 686096 (C4 (Web Text))

Max Activating Token Index: 303

Text #16

Max Range: 1.9379. Min Range: -1.9379

Max Act: 1.3835. Min Act: -0.0000

Data Index: 624585 (C4 (Web Text))

Max Activating Token Index: 594

Text #17

Max Range: 1.9379. Min Range: -1.9379

Max Act: 1.4570. Min Act: -0.0000

Data Index: 605924 (C4 (Web Text))

Max Activating Token Index: 276

Text #18

Max Range: 1.9379. Min Range: -1.9379

Max Act: 1.3765. Min Act: -0.0000

Data Index: 1482171 (Python Code)

Max Activating Token Index: 239

Text #19

Max Range: 1.9379. Min Range: -1.9379

Max Act: 1.5367. Min Act: -0.0000

Data Index: 44882 (C4 (Web Text))

Max Activating Token Index: 723