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

Dataset: The Pile

Neuron 1742 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: 0.6533. Min Range: -0.6533

Max Act: 0.6533. Min Act: -0.0000

Data Index: 1750120 (The Pile)

Max Activating Token Index: 356

Text #1

Max Range: 0.6533. Min Range: -0.6533

Max Act: 0.6400. Min Act: -0.0000

Data Index: 933341 (The Pile)

Max Activating Token Index: 213

Text #2

Max Range: 0.6533. Min Range: -0.6533

Max Act: 0.5497. Min Act: -0.0000

Data Index: 1512975 (The Pile)

Max Activating Token Index: 986

Text #3

Max Range: 0.6533. Min Range: -0.6533

Max Act: 0.5943. Min Act: -0.0000

Data Index: 1930534 (The Pile)

Max Activating Token Index: 234

Text #4

Max Range: 0.6533. Min Range: -0.6533

Max Act: 0.5832. Min Act: -0.0000

Data Index: 1839856 (The Pile)

Max Activating Token Index: 289

Text #5

Max Range: 0.6533. Min Range: -0.6533

Max Act: 0.5888. Min Act: -0.0000

Data Index: 176679 (The Pile)

Max Activating Token Index: 702

Text #6

Max Range: 0.6533. Min Range: -0.6533

Max Act: 0.5542. Min Act: -0.0000

Data Index: 1853602 (The Pile)

Max Activating Token Index: 181

Text #7

Max Range: 0.6533. Min Range: -0.6533

Max Act: 0.5371. Min Act: -0.0000

Data Index: 336520 (The Pile)

Max Activating Token Index: 53

Text #8

Max Range: 0.6533. Min Range: -0.6533

Max Act: 0.5580. Min Act: -0.0000

Data Index: 1142725 (The Pile)

Max Activating Token Index: 229

Text #9

Max Range: 0.6533. Min Range: -0.6533

Max Act: 0.5268. Min Act: -0.0000

Data Index: 6723 (The Pile)

Max Activating Token Index: 233

Text #10

Max Range: 0.6533. Min Range: -0.6533

Max Act: 0.5088. Min Act: -0.0000

Data Index: 870081 (The Pile)

Max Activating Token Index: 285

Text #11

Max Range: 0.6533. Min Range: -0.6533

Max Act: 0.5220. Min Act: -0.0000

Data Index: 1992185 (The Pile)

Max Activating Token Index: 41

Text #12

Max Range: 0.6533. Min Range: -0.6533

Max Act: 0.5141. Min Act: -0.0000

Data Index: 1146775 (The Pile)

Max Activating Token Index: 83

Text #13

Max Range: 0.6533. Min Range: -0.6533

Max Act: 0.5103. Min Act: -0.0000

Data Index: 476463 (The Pile)

Max Activating Token Index: 835

Text #14

Max Range: 0.6533. Min Range: -0.6533

Max Act: 0.5090. Min Act: -0.0000

Data Index: 1703552 (The Pile)

Max Activating Token Index: 244

Text #15

Max Range: 0.6533. Min Range: -0.6533

Max Act: 0.5153. Min Act: -0.0000

Data Index: 1328182 (The Pile)

Max Activating Token Index: 111

Text #16

Max Range: 0.6533. Min Range: -0.6533

Max Act: 0.4883. Min Act: -0.0000

Data Index: 1173612 (The Pile)

Max Activating Token Index: 604

Text #17

Max Range: 0.6533. Min Range: -0.6533

Max Act: 0.4819. Min Act: -0.0000

Data Index: 213920 (The Pile)

Max Activating Token Index: 205

Text #18

Max Range: 0.6533. Min Range: -0.6533

Max Act: 0.4647. Min Act: -0.0000

Data Index: 1453978 (The Pile)

Max Activating Token Index: 350

Text #19

Max Range: 0.6533. Min Range: -0.6533

Max Act: 0.4953. Min Act: -0.0000

Data Index: 113538 (The Pile)

Max Activating Token Index: 155