Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3124 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.0656. Min Range: -1.0656

Max Act: 1.0656. Min Act: -0.0000

Data Index: 1315764 (C4 (Web Text))

Max Activating Token Index: 849

Text #1

Max Range: 1.0656. Min Range: -1.0656

Max Act: 0.8211. Min Act: -0.0000

Data Index: 120111 (C4 (Web Text))

Max Activating Token Index: 860

Text #2

Max Range: 1.0656. Min Range: -1.0656

Max Act: 0.7421. Min Act: -0.0000

Data Index: 785206 (C4 (Web Text))

Max Activating Token Index: 208

Text #3

Max Range: 1.0656. Min Range: -1.0656

Max Act: 0.7680. Min Act: -0.0000

Data Index: 190000 (C4 (Web Text))

Max Activating Token Index: 742

Text #4

Max Range: 1.0656. Min Range: -1.0656

Max Act: 0.7174. Min Act: -0.0000

Data Index: 1228002 (C4 (Web Text))

Max Activating Token Index: 267

Text #5

Max Range: 1.0656. Min Range: -1.0656

Max Act: 0.6809. Min Act: -0.0000

Data Index: 1266737 (C4 (Web Text))

Max Activating Token Index: 966

Text #6

Max Range: 1.0656. Min Range: -1.0656

Max Act: 0.7180. Min Act: -0.0000

Data Index: 189597 (C4 (Web Text))

Max Activating Token Index: 579

Text #7

Max Range: 1.0656. Min Range: -1.0656

Max Act: 0.7214. Min Act: -0.0000

Data Index: 103938 (C4 (Web Text))

Max Activating Token Index: 99

Text #8

Max Range: 1.0656. Min Range: -1.0656

Max Act: 0.7155. Min Act: -0.0000

Data Index: 891167 (C4 (Web Text))

Max Activating Token Index: 412

Text #9

Max Range: 1.0656. Min Range: -1.0656

Max Act: 0.7117. Min Act: -0.0000

Data Index: 231123 (C4 (Web Text))

Max Activating Token Index: 1008

Text #10

Max Range: 1.0656. Min Range: -1.0656

Max Act: 0.6694. Min Act: -0.0000

Data Index: 163509 (C4 (Web Text))

Max Activating Token Index: 994

Text #11

Max Range: 1.0656. Min Range: -1.0656

Max Act: 0.6896. Min Act: -0.0000

Data Index: 859511 (C4 (Web Text))

Max Activating Token Index: 644

Text #12

Max Range: 1.0656. Min Range: -1.0656

Max Act: 0.6368. Min Act: -0.0000

Data Index: 867971 (C4 (Web Text))

Max Activating Token Index: 955

Text #13

Max Range: 1.0656. Min Range: -1.0656

Max Act: 0.6632. Min Act: -0.0000

Data Index: 3661 (C4 (Web Text))

Max Activating Token Index: 167

Text #14

Max Range: 1.0656. Min Range: -1.0656

Max Act: 0.6823. Min Act: -0.0000

Data Index: 789133 (C4 (Web Text))

Max Activating Token Index: 115

Text #15

Max Range: 1.0656. Min Range: -1.0656

Max Act: 0.6472. Min Act: -0.0000

Data Index: 968059 (C4 (Web Text))

Max Activating Token Index: 860

Text #16

Max Range: 1.0656. Min Range: -1.0656

Max Act: 0.6564. Min Act: -0.0000

Data Index: 1223625 (C4 (Web Text))

Max Activating Token Index: 649

Text #17

Max Range: 1.0656. Min Range: -1.0656

Max Act: 0.6309. Min Act: -0.0000

Data Index: 994778 (C4 (Web Text))

Max Activating Token Index: 792

Text #18

Max Range: 1.0656. Min Range: -1.0656

Max Act: 0.6450. Min Act: -0.0000

Data Index: 534836 (C4 (Web Text))

Max Activating Token Index: 719

Text #19

Max Range: 1.0656. Min Range: -1.0656

Max Act: 0.6173. Min Act: -0.0000

Data Index: 459031 (C4 (Web Text))

Max Activating Token Index: 213