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

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

Neuron 3400 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7157. Min Range: -0.7157

Max Act: 0.7157. Min Act: -0.0000

Data Index: 243823 (C4 (Web Text))

Max Activating Token Index: 59

Text #1

Max Range: 0.7157. Min Range: -0.7157

Max Act: 0.6300. Min Act: -0.0000

Data Index: 1082047 (C4 (Web Text))

Max Activating Token Index: 741

Text #2

Max Range: 0.7157. Min Range: -0.7157

Max Act: 0.4735. Min Act: -0.0000

Data Index: 1542950 (Python Code)

Max Activating Token Index: 652

Text #3

Max Range: 0.7157. Min Range: -0.7157

Max Act: 0.4537. Min Act: -0.0000

Data Index: 653121 (C4 (Web Text))

Max Activating Token Index: 702

Text #4

Max Range: 0.7157. Min Range: -0.7157

Max Act: 0.4843. Min Act: -0.0000

Data Index: 18426 (C4 (Web Text))

Max Activating Token Index: 113

Text #5

Max Range: 0.7157. Min Range: -0.7157

Max Act: 0.4560. Min Act: -0.0000

Data Index: 1488985 (Python Code)

Max Activating Token Index: 80

Text #6

Max Range: 0.7157. Min Range: -0.7157

Max Act: 0.3974. Min Act: -0.0000

Data Index: 1628203 (Python Code)

Max Activating Token Index: 10

Text #7

Max Range: 0.7157. Min Range: -0.7157

Max Act: 0.4072. Min Act: -0.0000

Data Index: 832629 (C4 (Web Text))

Max Activating Token Index: 985

Text #8

Max Range: 0.7157. Min Range: -0.7157

Max Act: 0.3814. Min Act: -0.0000

Data Index: 1215013 (C4 (Web Text))

Max Activating Token Index: 265

Text #9

Max Range: 0.7157. Min Range: -0.7157

Max Act: 0.3869. Min Act: -0.0000

Data Index: 64525 (C4 (Web Text))

Max Activating Token Index: 278

Text #10

Max Range: 0.7157. Min Range: -0.7157

Max Act: 0.3763. Min Act: -0.0000

Data Index: 1519521 (Python Code)

Max Activating Token Index: 623

Text #11

Max Range: 0.7157. Min Range: -0.7157

Max Act: 0.3919. Min Act: -0.0000

Data Index: 336241 (C4 (Web Text))

Max Activating Token Index: 671

Text #12

Max Range: 0.7157. Min Range: -0.7157

Max Act: 0.3717. Min Act: -0.0000

Data Index: 459351 (C4 (Web Text))

Max Activating Token Index: 450

Text #13

Max Range: 0.7157. Min Range: -0.7157

Max Act: 0.3834. Min Act: -0.0000

Data Index: 1415453 (Python Code)

Max Activating Token Index: 334

Text #14

Max Range: 0.7157. Min Range: -0.7157

Max Act: 0.3740. Min Act: -0.0000

Data Index: 686006 (C4 (Web Text))

Max Activating Token Index: 73

Text #15

Max Range: 0.7157. Min Range: -0.7157

Max Act: 0.3769. Min Act: -0.0000

Data Index: 1197182 (C4 (Web Text))

Max Activating Token Index: 970

Text #16

Max Range: 0.7157. Min Range: -0.7157

Max Act: 0.3719. Min Act: -0.0000

Data Index: 1299841 (C4 (Web Text))

Max Activating Token Index: 150

Text #17

Max Range: 0.7157. Min Range: -0.7157

Max Act: 0.3671. Min Act: -0.0000

Data Index: 578017 (C4 (Web Text))

Max Activating Token Index: 718

Text #18

Max Range: 0.7157. Min Range: -0.7157

Max Act: 0.3549. Min Act: -0.0000

Data Index: 537195 (C4 (Web Text))

Max Activating Token Index: 557

Text #19

Max Range: 0.7157. Min Range: -0.7157

Max Act: 0.3643. Min Act: -0.0000

Data Index: 1635705 (Python Code)

Max Activating Token Index: 189