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

Dataset: The Pile

Neuron 1904 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8137. Min Range: -0.8137

Max Act: 0.7990. Min Act: -0.0000

Data Index: 1223152 (The Pile)

Max Activating Token Index: 210

Text #1

Max Range: 0.8137. Min Range: -0.8137

Max Act: 0.8137. Min Act: -0.0000

Data Index: 340314 (The Pile)

Max Activating Token Index: 437

Text #2

Max Range: 0.8137. Min Range: -0.8137

Max Act: 0.7753. Min Act: -0.0000

Data Index: 1788182 (The Pile)

Max Activating Token Index: 217

Text #3

Max Range: 0.8137. Min Range: -0.8137

Max Act: 0.7721. Min Act: -0.0000

Data Index: 911987 (The Pile)

Max Activating Token Index: 149

Text #4

Max Range: 0.8137. Min Range: -0.8137

Max Act: 0.7275. Min Act: -0.0000

Data Index: 300319 (The Pile)

Max Activating Token Index: 384

Text #5

Max Range: 0.8137. Min Range: -0.8137

Max Act: 0.6702. Min Act: -0.0000

Data Index: 212827 (The Pile)

Max Activating Token Index: 447

Text #6

Max Range: 0.8137. Min Range: -0.8137

Max Act: 0.6763. Min Act: -0.0000

Data Index: 750440 (The Pile)

Max Activating Token Index: 500

Text #7

Max Range: 0.8137. Min Range: -0.8137

Max Act: 0.6019. Min Act: -0.0000

Data Index: 1028037 (The Pile)

Max Activating Token Index: 466

Text #8

Max Range: 0.8137. Min Range: -0.8137

Max Act: 0.5463. Min Act: -0.0000

Data Index: 47114 (The Pile)

Max Activating Token Index: 698

Text #9

Max Range: 0.8137. Min Range: -0.8137

Max Act: 0.5624. Min Act: -0.0000

Data Index: 1470650 (The Pile)

Max Activating Token Index: 295

Text #10

Max Range: 0.8137. Min Range: -0.8137

Max Act: 0.5474. Min Act: -0.0000

Data Index: 266772 (The Pile)

Max Activating Token Index: 193

Text #11

Max Range: 0.8137. Min Range: -0.8137

Max Act: 0.5257. Min Act: -0.0000

Data Index: 125994 (The Pile)

Max Activating Token Index: 271

Text #12

Max Range: 0.8137. Min Range: -0.8137

Max Act: 0.4940. Min Act: -0.0000

Data Index: 907146 (The Pile)

Max Activating Token Index: 761

Text #13

Max Range: 0.8137. Min Range: -0.8137

Max Act: 0.4812. Min Act: -0.0000

Data Index: 1872516 (The Pile)

Max Activating Token Index: 247

Text #14

Max Range: 0.8137. Min Range: -0.8137

Max Act: 0.4477. Min Act: -0.0000

Data Index: 1052165 (The Pile)

Max Activating Token Index: 889

Text #15

Max Range: 0.8137. Min Range: -0.8137

Max Act: 0.4858. Min Act: -0.0000

Data Index: 886269 (The Pile)

Max Activating Token Index: 84

Text #16

Max Range: 0.8137. Min Range: -0.8137

Max Act: 0.4951. Min Act: -0.0000

Data Index: 164976 (The Pile)

Max Activating Token Index: 391

Text #17

Max Range: 0.8137. Min Range: -0.8137

Max Act: 0.4504. Min Act: -0.0000

Data Index: 1604882 (The Pile)

Max Activating Token Index: 876

Text #18

Max Range: 0.8137. Min Range: -0.8137

Max Act: 0.4748. Min Act: -0.0000

Data Index: 1264415 (The Pile)

Max Activating Token Index: 29

Text #19

Max Range: 0.8137. Min Range: -0.8137

Max Act: 0.5024. Min Act: -0.0000

Data Index: 208602 (The Pile)

Max Activating Token Index: 871