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

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

Neuron 1520 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: 4.1745. Min Range: -4.1745

Max Act: 4.1745. Min Act: -0.0000

Data Index: 196107 (C4 (Web Text))

Max Activating Token Index: 193

Text #1

Max Range: 4.1745. Min Range: -4.1745

Max Act: 4.1504. Min Act: -0.0000

Data Index: 846196 (C4 (Web Text))

Max Activating Token Index: 155

Text #2

Max Range: 4.1745. Min Range: -4.1745

Max Act: 3.6988. Min Act: -0.0000

Data Index: 1229945 (C4 (Web Text))

Max Activating Token Index: 185

Text #3

Max Range: 4.1745. Min Range: -4.1745

Max Act: 3.7980. Min Act: -0.0000

Data Index: 914111 (C4 (Web Text))

Max Activating Token Index: 102

Text #4

Max Range: 4.1745. Min Range: -4.1745

Max Act: 3.5994. Min Act: -0.0000

Data Index: 74572 (C4 (Web Text))

Max Activating Token Index: 579

Text #5

Max Range: 4.1745. Min Range: -4.1745

Max Act: 3.6031. Min Act: -0.0000

Data Index: 1238025 (C4 (Web Text))

Max Activating Token Index: 113

Text #6

Max Range: 4.1745. Min Range: -4.1745

Max Act: 3.5711. Min Act: -0.0000

Data Index: 457835 (C4 (Web Text))

Max Activating Token Index: 517

Text #7

Max Range: 4.1745. Min Range: -4.1745

Max Act: 3.4749. Min Act: -0.0000

Data Index: 973937 (C4 (Web Text))

Max Activating Token Index: 878

Text #8

Max Range: 4.1745. Min Range: -4.1745

Max Act: 3.1024. Min Act: -0.0000

Data Index: 823316 (C4 (Web Text))

Max Activating Token Index: 636

Text #9

Max Range: 4.1745. Min Range: -4.1745

Max Act: 3.1592. Min Act: -0.0000

Data Index: 325062 (C4 (Web Text))

Max Activating Token Index: 445

Text #10

Max Range: 4.1745. Min Range: -4.1745

Max Act: 3.3442. Min Act: -0.0000

Data Index: 885050 (C4 (Web Text))

Max Activating Token Index: 353

Text #11

Max Range: 4.1745. Min Range: -4.1745

Max Act: 3.3520. Min Act: -0.0000

Data Index: 456526 (C4 (Web Text))

Max Activating Token Index: 979

Text #12

Max Range: 4.1745. Min Range: -4.1745

Max Act: 3.0334. Min Act: -0.0000

Data Index: 266460 (C4 (Web Text))

Max Activating Token Index: 498

Text #13

Max Range: 4.1745. Min Range: -4.1745

Max Act: 3.0167. Min Act: -0.0000

Data Index: 981553 (C4 (Web Text))

Max Activating Token Index: 566

Text #14

Max Range: 4.1745. Min Range: -4.1745

Max Act: 2.8417. Min Act: -0.0000

Data Index: 891594 (C4 (Web Text))

Max Activating Token Index: 517

Text #15

Max Range: 4.1745. Min Range: -4.1745

Max Act: 2.6586. Min Act: -0.0000

Data Index: 978967 (C4 (Web Text))

Max Activating Token Index: 690

Text #16

Max Range: 4.1745. Min Range: -4.1745

Max Act: 2.7065. Min Act: -0.0000

Data Index: 904055 (C4 (Web Text))

Max Activating Token Index: 802

Text #17

Max Range: 4.1745. Min Range: -4.1745

Max Act: 2.8089. Min Act: -0.0000

Data Index: 816690 (C4 (Web Text))

Max Activating Token Index: 828

Text #18

Max Range: 4.1745. Min Range: -4.1745

Max Act: 2.6477. Min Act: -0.0000

Data Index: 691895 (C4 (Web Text))

Max Activating Token Index: 562

Text #19

Max Range: 4.1745. Min Range: -4.1745

Max Act: 2.8685. Min Act: -0.0000

Data Index: 488806 (C4 (Web Text))

Max Activating Token Index: 952