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

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

Neuron 4898 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7579. Min Range: -0.7579

Max Act: 0.7579. Min Act: -0.0000

Data Index: 747766 (C4 (Web Text))

Max Activating Token Index: 351

Text #1

Max Range: 0.7579. Min Range: -0.7579

Max Act: 0.6809. Min Act: -0.0000

Data Index: 1167975 (C4 (Web Text))

Max Activating Token Index: 706

Text #2

Max Range: 0.7579. Min Range: -0.7579

Max Act: 0.6341. Min Act: -0.0000

Data Index: 401126 (C4 (Web Text))

Max Activating Token Index: 976

Text #3

Max Range: 0.7579. Min Range: -0.7579

Max Act: 0.6437. Min Act: -0.0000

Data Index: 437540 (C4 (Web Text))

Max Activating Token Index: 964

Text #4

Max Range: 0.7579. Min Range: -0.7579

Max Act: 0.5811. Min Act: -0.0000

Data Index: 422715 (C4 (Web Text))

Max Activating Token Index: 234

Text #5

Max Range: 0.7579. Min Range: -0.7579

Max Act: 0.5863. Min Act: -0.0000

Data Index: 953209 (C4 (Web Text))

Max Activating Token Index: 44

Text #6

Max Range: 0.7579. Min Range: -0.7579

Max Act: 0.5205. Min Act: -0.0000

Data Index: 341067 (C4 (Web Text))

Max Activating Token Index: 580

Text #7

Max Range: 0.7579. Min Range: -0.7579

Max Act: 0.5763. Min Act: -0.0000

Data Index: 1293661 (C4 (Web Text))

Max Activating Token Index: 617

Text #8

Max Range: 0.7579. Min Range: -0.7579

Max Act: 0.5789. Min Act: -0.0000

Data Index: 857665 (C4 (Web Text))

Max Activating Token Index: 212

Text #9

Max Range: 0.7579. Min Range: -0.7579

Max Act: 0.5522. Min Act: -0.0000

Data Index: 660791 (C4 (Web Text))

Max Activating Token Index: 310

Text #10

Max Range: 0.7579. Min Range: -0.7579

Max Act: 0.5172. Min Act: -0.0000

Data Index: 1189327 (C4 (Web Text))

Max Activating Token Index: 230

Text #11

Max Range: 0.7579. Min Range: -0.7579

Max Act: 0.5228. Min Act: -0.0000

Data Index: 1247175 (C4 (Web Text))

Max Activating Token Index: 62

Text #12

Max Range: 0.7579. Min Range: -0.7579

Max Act: 0.5202. Min Act: -0.0000

Data Index: 637510 (C4 (Web Text))

Max Activating Token Index: 673

Text #13

Max Range: 0.7579. Min Range: -0.7579

Max Act: 0.4940. Min Act: -0.0000

Data Index: 583766 (C4 (Web Text))

Max Activating Token Index: 139

Text #14

Max Range: 0.7579. Min Range: -0.7579

Max Act: 0.4929. Min Act: -0.0000

Data Index: 229852 (C4 (Web Text))

Max Activating Token Index: 720

Text #15

Max Range: 0.7579. Min Range: -0.7579

Max Act: 0.4887. Min Act: -0.0000

Data Index: 444773 (C4 (Web Text))

Max Activating Token Index: 127

Text #16

Max Range: 0.7579. Min Range: -0.7579

Max Act: 0.5323. Min Act: -0.0000

Data Index: 356707 (C4 (Web Text))

Max Activating Token Index: 761

Text #17

Max Range: 0.7579. Min Range: -0.7579

Max Act: 0.4950. Min Act: -0.0000

Data Index: 1055032 (C4 (Web Text))

Max Activating Token Index: 695

Text #18

Max Range: 0.7579. Min Range: -0.7579

Max Act: 0.4789. Min Act: -0.0000

Data Index: 552856 (C4 (Web Text))

Max Activating Token Index: 567

Text #19

Max Range: 0.7579. Min Range: -0.7579

Max Act: 0.4952. Min Act: 0.0000

Data Index: 868345 (C4 (Web Text))

Max Activating Token Index: 536