Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 225 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2207. Min Range: -0.2207

Max Act: 0.2207. Min Act: -0.0001

Data Index: 662167 (C4 (Web Text))

Max Activating Token Index: 31

Text #1

Max Range: 0.2207. Min Range: -0.2207

Max Act: 0.2027. Min Act: -0.0001

Data Index: 79350 (C4 (Web Text))

Max Activating Token Index: 886

Text #2

Max Range: 0.2207. Min Range: -0.2207

Max Act: 0.1850. Min Act: -0.0002

Data Index: 1158267 (C4 (Web Text))

Max Activating Token Index: 773

Text #3

Max Range: 0.2207. Min Range: -0.2207

Max Act: 0.1990. Min Act: -0.0002

Data Index: 1005547 (C4 (Web Text))

Max Activating Token Index: 32

Text #4

Max Range: 0.2207. Min Range: -0.2207

Max Act: 0.1910. Min Act: -0.0002

Data Index: 305773 (C4 (Web Text))

Max Activating Token Index: 680

Text #5

Max Range: 0.2207. Min Range: -0.2207

Max Act: 0.1998. Min Act: -0.0002

Data Index: 683483 (C4 (Web Text))

Max Activating Token Index: 127

Text #6

Max Range: 0.2207. Min Range: -0.2207

Max Act: 0.1922. Min Act: -0.0002

Data Index: 125065 (C4 (Web Text))

Max Activating Token Index: 384

Text #7

Max Range: 0.2207. Min Range: -0.2207

Max Act: 0.2066. Min Act: -0.0001

Data Index: 492032 (C4 (Web Text))

Max Activating Token Index: 242

Text #8

Max Range: 0.2207. Min Range: -0.2207

Max Act: 0.1970. Min Act: -0.0001

Data Index: 287726 (C4 (Web Text))

Max Activating Token Index: 442

Text #9

Max Range: 0.2207. Min Range: -0.2207

Max Act: 0.1896. Min Act: -0.0001

Data Index: 960526 (C4 (Web Text))

Max Activating Token Index: 368

Text #10

Max Range: 0.2207. Min Range: -0.2207

Max Act: 0.1805. Min Act: -0.0001

Data Index: 296615 (C4 (Web Text))

Max Activating Token Index: 856

Text #11

Max Range: 0.2207. Min Range: -0.2207

Max Act: 0.1936. Min Act: -0.0001

Data Index: 189628 (C4 (Web Text))

Max Activating Token Index: 654

Text #12

Max Range: 0.2207. Min Range: -0.2207

Max Act: 0.1756. Min Act: -0.0001

Data Index: 64674 (C4 (Web Text))

Max Activating Token Index: 75

Text #13

Max Range: 0.2207. Min Range: -0.2207

Max Act: 0.1741. Min Act: -0.0002

Data Index: 737536 (C4 (Web Text))

Max Activating Token Index: 640

Text #14

Max Range: 0.2207. Min Range: -0.2207

Max Act: 0.1721. Min Act: -0.0002

Data Index: 478532 (C4 (Web Text))

Max Activating Token Index: 406

Text #15

Max Range: 0.2207. Min Range: -0.2207

Max Act: 0.1795. Min Act: -0.0001

Data Index: 367469 (C4 (Web Text))

Max Activating Token Index: 474

Text #16

Max Range: 0.2207. Min Range: -0.2207

Max Act: 0.1746. Min Act: -0.0001

Data Index: 1031104 (C4 (Web Text))

Max Activating Token Index: 562

Text #17

Max Range: 0.2207. Min Range: -0.2207

Max Act: 0.1701. Min Act: -0.0001

Data Index: 515194 (C4 (Web Text))

Max Activating Token Index: 560

Text #18

Max Range: 0.2207. Min Range: -0.2207

Max Act: 0.1698. Min Act: -0.0001

Data Index: 1354737 (C4 (Web Text))

Max Activating Token Index: 900

Text #19

Max Range: 0.2207. Min Range: -0.2207

Max Act: 0.1571. Min Act: -0.0002

Data Index: 117978 (C4 (Web Text))

Max Activating Token Index: 876