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

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

Neuron 55 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.3519. Min Range: -6.3519

Max Act: 6.3519. Min Act: -0.0000

Data Index: 1320358 (C4 (Web Text))

Max Activating Token Index: 872

Text #1

Max Range: 6.3519. Min Range: -6.3519

Max Act: 6.3313. Min Act: -0.0000

Data Index: 532190 (C4 (Web Text))

Max Activating Token Index: 548

Text #2

Max Range: 6.3519. Min Range: -6.3519

Max Act: 6.1735. Min Act: -0.0000

Data Index: 82539 (C4 (Web Text))

Max Activating Token Index: 441

Text #3

Max Range: 6.3519. Min Range: -6.3519

Max Act: 6.1591. Min Act: -0.0000

Data Index: 393974 (C4 (Web Text))

Max Activating Token Index: 356

Text #4

Max Range: 6.3519. Min Range: -6.3519

Max Act: 6.0075. Min Act: -0.0000

Data Index: 162467 (C4 (Web Text))

Max Activating Token Index: 564

Text #5

Max Range: 6.3519. Min Range: -6.3519

Max Act: 6.0061. Min Act: -0.0000

Data Index: 751121 (C4 (Web Text))

Max Activating Token Index: 616

Text #6

Max Range: 6.3519. Min Range: -6.3519

Max Act: 6.1734. Min Act: -0.0000

Data Index: 341361 (C4 (Web Text))

Max Activating Token Index: 750

Text #7

Max Range: 6.3519. Min Range: -6.3519

Max Act: 5.8305. Min Act: -0.0000

Data Index: 1171684 (C4 (Web Text))

Max Activating Token Index: 556

Text #8

Max Range: 6.3519. Min Range: -6.3519

Max Act: 5.7770. Min Act: -0.0000

Data Index: 1331592 (C4 (Web Text))

Max Activating Token Index: 346

Text #9

Max Range: 6.3519. Min Range: -6.3519

Max Act: 5.4394. Min Act: -0.0000

Data Index: 998211 (C4 (Web Text))

Max Activating Token Index: 36

Text #10

Max Range: 6.3519. Min Range: -6.3519

Max Act: 5.4197. Min Act: -0.0000

Data Index: 215404 (C4 (Web Text))

Max Activating Token Index: 246

Text #11

Max Range: 6.3519. Min Range: -6.3519

Max Act: 5.2387. Min Act: -0.0000

Data Index: 773703 (C4 (Web Text))

Max Activating Token Index: 275

Text #12

Max Range: 6.3519. Min Range: -6.3519

Max Act: 4.5139. Min Act: -0.0000

Data Index: 2691 (C4 (Web Text))

Max Activating Token Index: 690

Text #13

Max Range: 6.3519. Min Range: -6.3519

Max Act: 4.3384. Min Act: -0.0000

Data Index: 49179 (C4 (Web Text))

Max Activating Token Index: 664

Text #14

Max Range: 6.3519. Min Range: -6.3519

Max Act: 4.4009. Min Act: -0.0000

Data Index: 952332 (C4 (Web Text))

Max Activating Token Index: 844

Text #15

Max Range: 6.3519. Min Range: -6.3519

Max Act: 4.3514. Min Act: -0.0000

Data Index: 307163 (C4 (Web Text))

Max Activating Token Index: 258

Text #16

Max Range: 6.3519. Min Range: -6.3519

Max Act: 4.3379. Min Act: -0.0000

Data Index: 349134 (C4 (Web Text))

Max Activating Token Index: 1008

Text #17

Max Range: 6.3519. Min Range: -6.3519

Max Act: 4.2846. Min Act: -0.0000

Data Index: 339485 (C4 (Web Text))

Max Activating Token Index: 1011

Text #18

Max Range: 6.3519. Min Range: -6.3519

Max Act: 4.2712. Min Act: -0.0000

Data Index: 481635 (C4 (Web Text))

Max Activating Token Index: 91

Text #19

Max Range: 6.3519. Min Range: -6.3519

Max Act: 4.0396. Min Act: -0.0000

Data Index: 572360 (C4 (Web Text))

Max Activating Token Index: 926