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

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

Neuron 2703 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0829. Min Range: -1.0829

Max Act: 1.0829. Min Act: -0.0001

Data Index: 999444 (C4 (Web Text))

Max Activating Token Index: 912

Text #1

Max Range: 1.0829. Min Range: -1.0829

Max Act: 0.9527. Min Act: -0.0001

Data Index: 68098 (C4 (Web Text))

Max Activating Token Index: 817

Text #2

Max Range: 1.0829. Min Range: -1.0829

Max Act: 0.8531. Min Act: -0.0001

Data Index: 908188 (C4 (Web Text))

Max Activating Token Index: 322

Text #3

Max Range: 1.0829. Min Range: -1.0829

Max Act: 0.9278. Min Act: -0.0001

Data Index: 414190 (C4 (Web Text))

Max Activating Token Index: 399

Text #4

Max Range: 1.0829. Min Range: -1.0829

Max Act: 0.8889. Min Act: -0.0001

Data Index: 544548 (C4 (Web Text))

Max Activating Token Index: 489

Text #5

Max Range: 1.0829. Min Range: -1.0829

Max Act: 0.7639. Min Act: -0.0001

Data Index: 12259 (C4 (Web Text))

Max Activating Token Index: 979

Text #6

Max Range: 1.0829. Min Range: -1.0829

Max Act: 0.6832. Min Act: -0.0001

Data Index: 393751 (C4 (Web Text))

Max Activating Token Index: 851

Text #7

Max Range: 1.0829. Min Range: -1.0829

Max Act: 0.7418. Min Act: -0.0001

Data Index: 1312200 (C4 (Web Text))

Max Activating Token Index: 791

Text #8

Max Range: 1.0829. Min Range: -1.0829

Max Act: 0.6835. Min Act: -0.0001

Data Index: 49134 (C4 (Web Text))

Max Activating Token Index: 258

Text #9

Max Range: 1.0829. Min Range: -1.0829

Max Act: 0.7986. Min Act: -0.0001

Data Index: 1000238 (C4 (Web Text))

Max Activating Token Index: 223

Text #10

Max Range: 1.0829. Min Range: -1.0829

Max Act: 0.7053. Min Act: -0.0001

Data Index: 1279133 (C4 (Web Text))

Max Activating Token Index: 294

Text #11

Max Range: 1.0829. Min Range: -1.0829

Max Act: 0.7101. Min Act: -0.0001

Data Index: 326552 (C4 (Web Text))

Max Activating Token Index: 715

Text #12

Max Range: 1.0829. Min Range: -1.0829

Max Act: 0.6814. Min Act: -0.0001

Data Index: 538038 (C4 (Web Text))

Max Activating Token Index: 385

Text #13

Max Range: 1.0829. Min Range: -1.0829

Max Act: 0.6478. Min Act: -0.0001

Data Index: 414876 (C4 (Web Text))

Max Activating Token Index: 764

Text #14

Max Range: 1.0829. Min Range: -1.0829

Max Act: 0.6426. Min Act: -0.0001

Data Index: 1252545 (C4 (Web Text))

Max Activating Token Index: 316

Text #15

Max Range: 1.0829. Min Range: -1.0829

Max Act: 0.7668. Min Act: -0.0001

Data Index: 854912 (C4 (Web Text))

Max Activating Token Index: 539

Text #16

Max Range: 1.0829. Min Range: -1.0829

Max Act: 0.6722. Min Act: -0.0001

Data Index: 404241 (C4 (Web Text))

Max Activating Token Index: 811

Text #17

Max Range: 1.0829. Min Range: -1.0829

Max Act: 0.6258. Min Act: -0.0001

Data Index: 1127864 (C4 (Web Text))

Max Activating Token Index: 474

Text #18

Max Range: 1.0829. Min Range: -1.0829

Max Act: 0.5567. Min Act: -0.0001

Data Index: 1161268 (C4 (Web Text))

Max Activating Token Index: 997

Text #19

Max Range: 1.0829. Min Range: -1.0829

Max Act: 0.6033. Min Act: -0.0001

Data Index: 387918 (C4 (Web Text))

Max Activating Token Index: 173