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

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

Neuron 3481 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9021. Min Range: -0.9021

Max Act: 0.9021. Min Act: -0.0000

Data Index: 86132 (C4 (Web Text))

Max Activating Token Index: 966

Text #1

Max Range: 0.9021. Min Range: -0.9021

Max Act: 0.8080. Min Act: -0.0000

Data Index: 647794 (C4 (Web Text))

Max Activating Token Index: 726

Text #2

Max Range: 0.9021. Min Range: -0.9021

Max Act: 0.8387. Min Act: -0.0000

Data Index: 565760 (C4 (Web Text))

Max Activating Token Index: 753

Text #3

Max Range: 0.9021. Min Range: -0.9021

Max Act: 0.7687. Min Act: -0.0000

Data Index: 96896 (C4 (Web Text))

Max Activating Token Index: 1019

Text #4

Max Range: 0.9021. Min Range: -0.9021

Max Act: 0.6599. Min Act: -0.0000

Data Index: 839883 (C4 (Web Text))

Max Activating Token Index: 757

Text #5

Max Range: 0.9021. Min Range: -0.9021

Max Act: 0.6892. Min Act: -0.0000

Data Index: 1276026 (C4 (Web Text))

Max Activating Token Index: 526

Text #6

Max Range: 0.9021. Min Range: -0.9021

Max Act: 0.6971. Min Act: -0.0000

Data Index: 188112 (C4 (Web Text))

Max Activating Token Index: 357

Text #7

Max Range: 0.9021. Min Range: -0.9021

Max Act: 0.6670. Min Act: -0.0000

Data Index: 260948 (C4 (Web Text))

Max Activating Token Index: 378

Text #8

Max Range: 0.9021. Min Range: -0.9021

Max Act: 0.6348. Min Act: -0.0000

Data Index: 273997 (C4 (Web Text))

Max Activating Token Index: 405

Text #9

Max Range: 0.9021. Min Range: -0.9021

Max Act: 0.5875. Min Act: -0.0000

Data Index: 957454 (C4 (Web Text))

Max Activating Token Index: 986

Text #10

Max Range: 0.9021. Min Range: -0.9021

Max Act: 0.6077. Min Act: -0.0000

Data Index: 453629 (C4 (Web Text))

Max Activating Token Index: 440

Text #11

Max Range: 0.9021. Min Range: -0.9021

Max Act: 0.6006. Min Act: -0.0000

Data Index: 240819 (C4 (Web Text))

Max Activating Token Index: 302

Text #12

Max Range: 0.9021. Min Range: -0.9021

Max Act: 0.5154. Min Act: -0.0000

Data Index: 1317519 (C4 (Web Text))

Max Activating Token Index: 93

Text #13

Max Range: 0.9021. Min Range: -0.9021

Max Act: 0.4551. Min Act: -0.0000

Data Index: 1278982 (C4 (Web Text))

Max Activating Token Index: 679

Text #14

Max Range: 0.9021. Min Range: -0.9021

Max Act: 0.4684. Min Act: -0.0000

Data Index: 130821 (C4 (Web Text))

Max Activating Token Index: 787

Text #15

Max Range: 0.9021. Min Range: -0.9021

Max Act: 0.4444. Min Act: -0.0000

Data Index: 78297 (C4 (Web Text))

Max Activating Token Index: 426

Text #16

Max Range: 0.9021. Min Range: -0.9021

Max Act: 0.4432. Min Act: -0.0000

Data Index: 432657 (C4 (Web Text))

Max Activating Token Index: 711

Text #17

Max Range: 0.9021. Min Range: -0.9021

Max Act: 0.4147. Min Act: -0.0000

Data Index: 174595 (C4 (Web Text))

Max Activating Token Index: 65

Text #18

Max Range: 0.9021. Min Range: -0.9021

Max Act: 0.3862. Min Act: -0.0000

Data Index: 70528 (C4 (Web Text))

Max Activating Token Index: 611

Text #19

Max Range: 0.9021. Min Range: -0.9021

Max Act: 0.3931. Min Act: -0.0000

Data Index: 956810 (C4 (Web Text))

Max Activating Token Index: 453