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

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

Neuron 3057 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.9686. Min Range: -4.9686

Max Act: 4.9686. Min Act: -0.0000

Data Index: 1093404 (C4 (Web Text))

Max Activating Token Index: 533

Text #1

Max Range: 4.9686. Min Range: -4.9686

Max Act: 4.8617. Min Act: -0.0000

Data Index: 987198 (C4 (Web Text))

Max Activating Token Index: 211

Text #2

Max Range: 4.9686. Min Range: -4.9686

Max Act: 4.6041. Min Act: -0.0000

Data Index: 397055 (C4 (Web Text))

Max Activating Token Index: 64

Text #3

Max Range: 4.9686. Min Range: -4.9686

Max Act: 4.5089. Min Act: -0.0000

Data Index: 294923 (C4 (Web Text))

Max Activating Token Index: 200

Text #4

Max Range: 4.9686. Min Range: -4.9686

Max Act: 4.7009. Min Act: -0.0000

Data Index: 570281 (C4 (Web Text))

Max Activating Token Index: 156

Text #5

Max Range: 4.9686. Min Range: -4.9686

Max Act: 4.7132. Min Act: -0.0000

Data Index: 890471 (C4 (Web Text))

Max Activating Token Index: 41

Text #6

Max Range: 4.9686. Min Range: -4.9686

Max Act: 4.4972. Min Act: -0.0000

Data Index: 55666 (C4 (Web Text))

Max Activating Token Index: 160

Text #7

Max Range: 4.9686. Min Range: -4.9686

Max Act: 4.4881. Min Act: -0.0000

Data Index: 496003 (C4 (Web Text))

Max Activating Token Index: 223

Text #8

Max Range: 4.9686. Min Range: -4.9686

Max Act: 4.3316. Min Act: -0.0000

Data Index: 458532 (C4 (Web Text))

Max Activating Token Index: 144

Text #9

Max Range: 4.9686. Min Range: -4.9686

Max Act: 4.6645. Min Act: -0.0000

Data Index: 739233 (C4 (Web Text))

Max Activating Token Index: 121

Text #10

Max Range: 4.9686. Min Range: -4.9686

Max Act: 4.2477. Min Act: -0.0000

Data Index: 885934 (C4 (Web Text))

Max Activating Token Index: 121

Text #11

Max Range: 4.9686. Min Range: -4.9686

Max Act: 4.1653. Min Act: -0.0000

Data Index: 1073834 (C4 (Web Text))

Max Activating Token Index: 82

Text #12

Max Range: 4.9686. Min Range: -4.9686

Max Act: 4.1338. Min Act: -0.0000

Data Index: 825030 (C4 (Web Text))

Max Activating Token Index: 865

Text #13

Max Range: 4.9686. Min Range: -4.9686

Max Act: 4.2744. Min Act: -0.0000

Data Index: 263515 (C4 (Web Text))

Max Activating Token Index: 906

Text #14

Max Range: 4.9686. Min Range: -4.9686

Max Act: 4.1034. Min Act: -0.0000

Data Index: 874974 (C4 (Web Text))

Max Activating Token Index: 35

Text #15

Max Range: 4.9686. Min Range: -4.9686

Max Act: 3.7300. Min Act: -0.0000

Data Index: 63081 (C4 (Web Text))

Max Activating Token Index: 816

Text #16

Max Range: 4.9686. Min Range: -4.9686

Max Act: 4.0282. Min Act: -0.0000

Data Index: 433467 (C4 (Web Text))

Max Activating Token Index: 144

Text #17

Max Range: 4.9686. Min Range: -4.9686

Max Act: 3.8267. Min Act: -0.0000

Data Index: 658179 (C4 (Web Text))

Max Activating Token Index: 302

Text #18

Max Range: 4.9686. Min Range: -4.9686

Max Act: 4.0103. Min Act: -0.0000

Data Index: 1154437 (C4 (Web Text))

Max Activating Token Index: 680

Text #19

Max Range: 4.9686. Min Range: -4.9686

Max Act: 3.9608. Min Act: -0.0000

Data Index: 1113719 (C4 (Web Text))

Max Activating Token Index: 312