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

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

Neuron 3723 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4997. Min Range: -0.4997

Max Act: 0.4997. Min Act: -0.0000

Data Index: 1055152 (C4 (Web Text))

Max Activating Token Index: 279

Text #1

Max Range: 0.4997. Min Range: -0.4997

Max Act: 0.4740. Min Act: -0.0000

Data Index: 386886 (C4 (Web Text))

Max Activating Token Index: 577

Text #2

Max Range: 0.4997. Min Range: -0.4997

Max Act: 0.4228. Min Act: -0.0000

Data Index: 1645807 (Python Code)

Max Activating Token Index: 834

Text #3

Max Range: 0.4997. Min Range: -0.4997

Max Act: 0.4172. Min Act: -0.0000

Data Index: 728287 (C4 (Web Text))

Max Activating Token Index: 365

Text #4

Max Range: 0.4997. Min Range: -0.4997

Max Act: 0.4071. Min Act: -0.0000

Data Index: 774162 (C4 (Web Text))

Max Activating Token Index: 726

Text #5

Max Range: 0.4997. Min Range: -0.4997

Max Act: 0.3400. Min Act: -0.0000

Data Index: 336080 (C4 (Web Text))

Max Activating Token Index: 753

Text #6

Max Range: 0.4997. Min Range: -0.4997

Max Act: 0.4193. Min Act: -0.0000

Data Index: 1597122 (Python Code)

Max Activating Token Index: 33

Text #7

Max Range: 0.4997. Min Range: -0.4997

Max Act: 0.3916. Min Act: -0.0000

Data Index: 757600 (C4 (Web Text))

Max Activating Token Index: 251

Text #8

Max Range: 0.4997. Min Range: -0.4997

Max Act: 0.4390. Min Act: -0.0000

Data Index: 1533470 (Python Code)

Max Activating Token Index: 149

Text #9

Max Range: 0.4997. Min Range: -0.4997

Max Act: 0.4015. Min Act: -0.0000

Data Index: 1434977 (Python Code)

Max Activating Token Index: 147

Text #10

Max Range: 0.4997. Min Range: -0.4997

Max Act: 0.4076. Min Act: -0.0000

Data Index: 1428257 (Python Code)

Max Activating Token Index: 162

Text #11

Max Range: 0.4997. Min Range: -0.4997

Max Act: 0.4218. Min Act: -0.0000

Data Index: 1362591 (Python Code)

Max Activating Token Index: 184

Text #12

Max Range: 0.4997. Min Range: -0.4997

Max Act: 0.4195. Min Act: -0.0000

Data Index: 1557070 (Python Code)

Max Activating Token Index: 560

Text #13

Max Range: 0.4997. Min Range: -0.4997

Max Act: 0.4031. Min Act: -0.0000

Data Index: 1404565 (Python Code)

Max Activating Token Index: 625

Text #14

Max Range: 0.4997. Min Range: -0.4997

Max Act: 0.3834. Min Act: -0.0000

Data Index: 991696 (C4 (Web Text))

Max Activating Token Index: 216

Text #15

Max Range: 0.4997. Min Range: -0.4997

Max Act: 0.3865. Min Act: -0.0000

Data Index: 184822 (C4 (Web Text))

Max Activating Token Index: 857

Text #16

Max Range: 0.4997. Min Range: -0.4997

Max Act: 0.3650. Min Act: -0.0000

Data Index: 195435 (C4 (Web Text))

Max Activating Token Index: 951

Text #17

Max Range: 0.4997. Min Range: -0.4997

Max Act: 0.3693. Min Act: -0.0000

Data Index: 1584734 (Python Code)

Max Activating Token Index: 87

Text #18

Max Range: 0.4997. Min Range: -0.4997

Max Act: 0.3734. Min Act: -0.0000

Data Index: 1654230 (Python Code)

Max Activating Token Index: 327

Text #19

Max Range: 0.4997. Min Range: -0.4997

Max Act: 0.3783. Min Act: -0.0000

Data Index: 1378723 (Python Code)

Max Activating Token Index: 14