Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 747 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5666. Min Range: -0.5666

Max Act: 0.5666. Min Act: -0.0002

Data Index: 963990 (C4 (Web Text))

Max Activating Token Index: 117

Text #1

Max Range: 0.5666. Min Range: -0.5666

Max Act: 0.5636. Min Act: -0.0001

Data Index: 87025 (C4 (Web Text))

Max Activating Token Index: 916

Text #2

Max Range: 0.5666. Min Range: -0.5666

Max Act: 0.4744. Min Act: -0.0001

Data Index: 29477 (C4 (Web Text))

Max Activating Token Index: 621

Text #3

Max Range: 0.5666. Min Range: -0.5666

Max Act: 0.4851. Min Act: -0.0002

Data Index: 967073 (C4 (Web Text))

Max Activating Token Index: 777

Text #4

Max Range: 0.5666. Min Range: -0.5666

Max Act: 0.4719. Min Act: -0.0002

Data Index: 187463 (C4 (Web Text))

Max Activating Token Index: 704

Text #5

Max Range: 0.5666. Min Range: -0.5666

Max Act: 0.4622. Min Act: -0.0002

Data Index: 24729 (C4 (Web Text))

Max Activating Token Index: 158

Text #6

Max Range: 0.5666. Min Range: -0.5666

Max Act: 0.4691. Min Act: -0.0002

Data Index: 485003 (C4 (Web Text))

Max Activating Token Index: 433

Text #7

Max Range: 0.5666. Min Range: -0.5666

Max Act: 0.4800. Min Act: -0.0002

Data Index: 997066 (C4 (Web Text))

Max Activating Token Index: 862

Text #8

Max Range: 0.5666. Min Range: -0.5666

Max Act: 0.4178. Min Act: -0.0001

Data Index: 14235 (C4 (Web Text))

Max Activating Token Index: 666

Text #9

Max Range: 0.5666. Min Range: -0.5666

Max Act: 0.3770. Min Act: -0.0001

Data Index: 1282190 (C4 (Web Text))

Max Activating Token Index: 918

Text #10

Max Range: 0.5666. Min Range: -0.5666

Max Act: 0.4572. Min Act: -0.0002

Data Index: 1285012 (C4 (Web Text))

Max Activating Token Index: 193

Text #11

Max Range: 0.5666. Min Range: -0.5666

Max Act: 0.4506. Min Act: -0.0001

Data Index: 521245 (C4 (Web Text))

Max Activating Token Index: 214

Text #12

Max Range: 0.5666. Min Range: -0.5666

Max Act: 0.4491. Min Act: -0.0002

Data Index: 691624 (C4 (Web Text))

Max Activating Token Index: 173

Text #13

Max Range: 0.5666. Min Range: -0.5666

Max Act: 0.3819. Min Act: -0.0002

Data Index: 30585 (C4 (Web Text))

Max Activating Token Index: 575

Text #14

Max Range: 0.5666. Min Range: -0.5666

Max Act: 0.4295. Min Act: -0.0002

Data Index: 526692 (C4 (Web Text))

Max Activating Token Index: 1003

Text #15

Max Range: 0.5666. Min Range: -0.5666

Max Act: 0.4243. Min Act: -0.0002

Data Index: 697231 (C4 (Web Text))

Max Activating Token Index: 137

Text #16

Max Range: 0.5666. Min Range: -0.5666

Max Act: 0.4501. Min Act: -0.0001

Data Index: 387794 (C4 (Web Text))

Max Activating Token Index: 254

Text #17

Max Range: 0.5666. Min Range: -0.5666

Max Act: 0.4056. Min Act: -0.0002

Data Index: 665030 (C4 (Web Text))

Max Activating Token Index: 570

Text #18

Max Range: 0.5666. Min Range: -0.5666

Max Act: 0.4651. Min Act: -0.0002

Data Index: 263538 (C4 (Web Text))

Max Activating Token Index: 844

Text #19

Max Range: 0.5666. Min Range: -0.5666

Max Act: 0.4159. Min Act: -0.0001

Data Index: 521674 (C4 (Web Text))

Max Activating Token Index: 426