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

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

Neuron 1515 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: 2.0913. Min Range: -2.0913

Max Act: 2.0913. Min Act: -0.0000

Data Index: 477555 (C4 (Web Text))

Max Activating Token Index: 477

Text #1

Max Range: 2.0913. Min Range: -2.0913

Max Act: 1.7580. Min Act: -0.0000

Data Index: 259534 (C4 (Web Text))

Max Activating Token Index: 566

Text #2

Max Range: 2.0913. Min Range: -2.0913

Max Act: 1.4822. Min Act: -0.0000

Data Index: 1106986 (C4 (Web Text))

Max Activating Token Index: 693

Text #3

Max Range: 2.0913. Min Range: -2.0913

Max Act: 1.5558. Min Act: -0.0000

Data Index: 1108560 (C4 (Web Text))

Max Activating Token Index: 627

Text #4

Max Range: 2.0913. Min Range: -2.0913

Max Act: 1.5503. Min Act: -0.0000

Data Index: 640791 (C4 (Web Text))

Max Activating Token Index: 375

Text #5

Max Range: 2.0913. Min Range: -2.0913

Max Act: 1.5147. Min Act: -0.0000

Data Index: 162919 (C4 (Web Text))

Max Activating Token Index: 59

Text #6

Max Range: 2.0913. Min Range: -2.0913

Max Act: 1.4955. Min Act: -0.0000

Data Index: 934668 (C4 (Web Text))

Max Activating Token Index: 422

Text #7

Max Range: 2.0913. Min Range: -2.0913

Max Act: 1.5894. Min Act: -0.0000

Data Index: 651379 (C4 (Web Text))

Max Activating Token Index: 1002

Text #8

Max Range: 2.0913. Min Range: -2.0913

Max Act: 1.4122. Min Act: -0.0000

Data Index: 1139197 (C4 (Web Text))

Max Activating Token Index: 419

Text #9

Max Range: 2.0913. Min Range: -2.0913

Max Act: 1.4359. Min Act: -0.0000

Data Index: 1290421 (C4 (Web Text))

Max Activating Token Index: 301

Text #10

Max Range: 2.0913. Min Range: -2.0913

Max Act: 1.4687. Min Act: -0.0000

Data Index: 170972 (C4 (Web Text))

Max Activating Token Index: 450

Text #11

Max Range: 2.0913. Min Range: -2.0913

Max Act: 1.4661. Min Act: -0.0000

Data Index: 858571 (C4 (Web Text))

Max Activating Token Index: 376

Text #12

Max Range: 2.0913. Min Range: -2.0913

Max Act: 1.4202. Min Act: -0.0000

Data Index: 441223 (C4 (Web Text))

Max Activating Token Index: 366

Text #13

Max Range: 2.0913. Min Range: -2.0913

Max Act: 1.4519. Min Act: -0.0000

Data Index: 1119598 (C4 (Web Text))

Max Activating Token Index: 120

Text #14

Max Range: 2.0913. Min Range: -2.0913

Max Act: 1.3875. Min Act: -0.0000

Data Index: 269675 (C4 (Web Text))

Max Activating Token Index: 481

Text #15

Max Range: 2.0913. Min Range: -2.0913

Max Act: 1.2837. Min Act: -0.0000

Data Index: 72175 (C4 (Web Text))

Max Activating Token Index: 584

Text #16

Max Range: 2.0913. Min Range: -2.0913

Max Act: 1.3003. Min Act: -0.0000

Data Index: 536189 (C4 (Web Text))

Max Activating Token Index: 375

Text #17

Max Range: 2.0913. Min Range: -2.0913

Max Act: 1.1814. Min Act: -0.0000

Data Index: 943943 (C4 (Web Text))

Max Activating Token Index: 509

Text #18

Max Range: 2.0913. Min Range: -2.0913

Max Act: 1.3596. Min Act: -0.0000

Data Index: 331861 (C4 (Web Text))

Max Activating Token Index: 612

Text #19

Max Range: 2.0913. Min Range: -2.0913

Max Act: 1.1548. Min Act: -0.0000

Data Index: 484508 (C4 (Web Text))

Max Activating Token Index: 1012