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

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

Neuron 4029 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: 0.4643. Min Range: -0.4643

Max Act: 0.4643. Min Act: -0.0000

Data Index: 726584 (C4 (Web Text))

Max Activating Token Index: 530

Text #1

Max Range: 0.4643. Min Range: -0.4643

Max Act: 0.4378. Min Act: -0.0000

Data Index: 577804 (C4 (Web Text))

Max Activating Token Index: 547

Text #2

Max Range: 0.4643. Min Range: -0.4643

Max Act: 0.4232. Min Act: -0.0000

Data Index: 1242634 (C4 (Web Text))

Max Activating Token Index: 407

Text #3

Max Range: 0.4643. Min Range: -0.4643

Max Act: 0.4211. Min Act: -0.0000

Data Index: 1115127 (C4 (Web Text))

Max Activating Token Index: 445

Text #4

Max Range: 0.4643. Min Range: -0.4643

Max Act: 0.4248. Min Act: -0.0000

Data Index: 805420 (C4 (Web Text))

Max Activating Token Index: 983

Text #5

Max Range: 0.4643. Min Range: -0.4643

Max Act: 0.4072. Min Act: -0.0000

Data Index: 811493 (C4 (Web Text))

Max Activating Token Index: 730

Text #6

Max Range: 0.4643. Min Range: -0.4643

Max Act: 0.4193. Min Act: -0.0000

Data Index: 426 (C4 (Web Text))

Max Activating Token Index: 412

Text #7

Max Range: 0.4643. Min Range: -0.4643

Max Act: 0.4107. Min Act: -0.0000

Data Index: 715203 (C4 (Web Text))

Max Activating Token Index: 375

Text #8

Max Range: 0.4643. Min Range: -0.4643

Max Act: 0.4429. Min Act: -0.0000

Data Index: 316178 (C4 (Web Text))

Max Activating Token Index: 148

Text #9

Max Range: 0.4643. Min Range: -0.4643

Max Act: 0.4111. Min Act: -0.0000

Data Index: 66000 (C4 (Web Text))

Max Activating Token Index: 125

Text #10

Max Range: 0.4643. Min Range: -0.4643

Max Act: 0.4094. Min Act: -0.0000

Data Index: 27469 (C4 (Web Text))

Max Activating Token Index: 635

Text #11

Max Range: 0.4643. Min Range: -0.4643

Max Act: 0.4084. Min Act: 0.0000

Data Index: 93149 (C4 (Web Text))

Max Activating Token Index: 886

Text #12

Max Range: 0.4643. Min Range: -0.4643

Max Act: 0.4047. Min Act: -0.0000

Data Index: 379672 (C4 (Web Text))

Max Activating Token Index: 381

Text #13

Max Range: 0.4643. Min Range: -0.4643

Max Act: 0.4045. Min Act: -0.0000

Data Index: 207194 (C4 (Web Text))

Max Activating Token Index: 453

Text #14

Max Range: 0.4643. Min Range: -0.4643

Max Act: 0.4165. Min Act: -0.0000

Data Index: 825013 (C4 (Web Text))

Max Activating Token Index: 448

Text #15

Max Range: 0.4643. Min Range: -0.4643

Max Act: 0.3978. Min Act: -0.0000

Data Index: 128905 (C4 (Web Text))

Max Activating Token Index: 431

Text #16

Max Range: 0.4643. Min Range: -0.4643

Max Act: 0.3747. Min Act: -0.0000

Data Index: 153194 (C4 (Web Text))

Max Activating Token Index: 194

Text #17

Max Range: 0.4643. Min Range: -0.4643

Max Act: 0.3952. Min Act: -0.0000

Data Index: 61626 (C4 (Web Text))

Max Activating Token Index: 461

Text #18

Max Range: 0.4643. Min Range: -0.4643

Max Act: 0.3928. Min Act: -0.0000

Data Index: 692194 (C4 (Web Text))

Max Activating Token Index: 259

Text #19

Max Range: 0.4643. Min Range: -0.4643

Max Act: 0.3875. Min Act: -0.0000

Data Index: 209948 (C4 (Web Text))

Max Activating Token Index: 764