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

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

Neuron 2552 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3849. Min Range: -1.3849

Max Act: 1.3849. Min Act: -0.0002

Data Index: 1166945 (C4 (Web Text))

Max Activating Token Index: 101

Text #1

Max Range: 1.3849. Min Range: -1.3849

Max Act: 1.3055. Min Act: -0.0002

Data Index: 152002 (C4 (Web Text))

Max Activating Token Index: 272

Text #2

Max Range: 1.3849. Min Range: -1.3849

Max Act: 1.2246. Min Act: -0.0002

Data Index: 929835 (C4 (Web Text))

Max Activating Token Index: 260

Text #3

Max Range: 1.3849. Min Range: -1.3849

Max Act: 1.0959. Min Act: -0.0002

Data Index: 1123595 (C4 (Web Text))

Max Activating Token Index: 335

Text #4

Max Range: 1.3849. Min Range: -1.3849

Max Act: 1.2962. Min Act: -0.0002

Data Index: 387754 (C4 (Web Text))

Max Activating Token Index: 76

Text #5

Max Range: 1.3849. Min Range: -1.3849

Max Act: 1.1327. Min Act: -0.0002

Data Index: 893237 (C4 (Web Text))

Max Activating Token Index: 738

Text #6

Max Range: 1.3849. Min Range: -1.3849

Max Act: 1.2005. Min Act: -0.0002

Data Index: 1097201 (C4 (Web Text))

Max Activating Token Index: 232

Text #7

Max Range: 1.3849. Min Range: -1.3849

Max Act: 1.1038. Min Act: -0.0002

Data Index: 536815 (C4 (Web Text))

Max Activating Token Index: 914

Text #8

Max Range: 1.3849. Min Range: -1.3849

Max Act: 1.0833. Min Act: -0.0002

Data Index: 958987 (C4 (Web Text))

Max Activating Token Index: 255

Text #9

Max Range: 1.3849. Min Range: -1.3849

Max Act: 1.1332. Min Act: -0.0002

Data Index: 1279969 (C4 (Web Text))

Max Activating Token Index: 422

Text #10

Max Range: 1.3849. Min Range: -1.3849

Max Act: 1.1242. Min Act: -0.0002

Data Index: 950220 (C4 (Web Text))

Max Activating Token Index: 15

Text #11

Max Range: 1.3849. Min Range: -1.3849

Max Act: 0.9566. Min Act: -0.0002

Data Index: 340774 (C4 (Web Text))

Max Activating Token Index: 811

Text #12

Max Range: 1.3849. Min Range: -1.3849

Max Act: 1.1957. Min Act: -0.0002

Data Index: 1279520 (C4 (Web Text))

Max Activating Token Index: 92

Text #13

Max Range: 1.3849. Min Range: -1.3849

Max Act: 0.9604. Min Act: -0.0002

Data Index: 159600 (C4 (Web Text))

Max Activating Token Index: 128

Text #14

Max Range: 1.3849. Min Range: -1.3849

Max Act: 1.2916. Min Act: -0.0002

Data Index: 1211339 (C4 (Web Text))

Max Activating Token Index: 85

Text #15

Max Range: 1.3849. Min Range: -1.3849

Max Act: 1.1651. Min Act: -0.0002

Data Index: 1162419 (C4 (Web Text))

Max Activating Token Index: 527

Text #16

Max Range: 1.3849. Min Range: -1.3849

Max Act: 1.2102. Min Act: -0.0002

Data Index: 517325 (C4 (Web Text))

Max Activating Token Index: 67

Text #17

Max Range: 1.3849. Min Range: -1.3849

Max Act: 1.0793. Min Act: -0.0002

Data Index: 4771 (C4 (Web Text))

Max Activating Token Index: 139

Text #18

Max Range: 1.3849. Min Range: -1.3849

Max Act: 0.9606. Min Act: -0.0002

Data Index: 697803 (C4 (Web Text))

Max Activating Token Index: 497

Text #19

Max Range: 1.3849. Min Range: -1.3849

Max Act: 0.9078. Min Act: -0.0002

Data Index: 103355 (C4 (Web Text))

Max Activating Token Index: 391