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

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

Neuron 444 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7958. Min Range: -1.7958

Max Act: 1.7958. Min Act: -0.0000

Data Index: 1243457 (C4 (Web Text))

Max Activating Token Index: 277

Text #1

Max Range: 1.7958. Min Range: -1.7958

Max Act: 1.5553. Min Act: -0.0000

Data Index: 1307564 (C4 (Web Text))

Max Activating Token Index: 436

Text #2

Max Range: 1.7958. Min Range: -1.7958

Max Act: 1.5916. Min Act: -0.0000

Data Index: 1280661 (C4 (Web Text))

Max Activating Token Index: 300

Text #3

Max Range: 1.7958. Min Range: -1.7958

Max Act: 1.4065. Min Act: -0.0000

Data Index: 1014016 (C4 (Web Text))

Max Activating Token Index: 244

Text #4

Max Range: 1.7958. Min Range: -1.7958

Max Act: 1.3770. Min Act: -0.0000

Data Index: 1084710 (C4 (Web Text))

Max Activating Token Index: 627

Text #5

Max Range: 1.7958. Min Range: -1.7958

Max Act: 1.5261. Min Act: -0.0000

Data Index: 49922 (C4 (Web Text))

Max Activating Token Index: 860

Text #6

Max Range: 1.7958. Min Range: -1.7958

Max Act: 1.2677. Min Act: -0.0000

Data Index: 996996 (C4 (Web Text))

Max Activating Token Index: 963

Text #7

Max Range: 1.7958. Min Range: -1.7958

Max Act: 1.3022. Min Act: -0.0000

Data Index: 968571 (C4 (Web Text))

Max Activating Token Index: 164

Text #8

Max Range: 1.7958. Min Range: -1.7958

Max Act: 1.2008. Min Act: -0.0000

Data Index: 20628 (C4 (Web Text))

Max Activating Token Index: 724

Text #9

Max Range: 1.7958. Min Range: -1.7958

Max Act: 1.1562. Min Act: -0.0000

Data Index: 73509 (C4 (Web Text))

Max Activating Token Index: 562

Text #10

Max Range: 1.7958. Min Range: -1.7958

Max Act: 1.1721. Min Act: -0.0000

Data Index: 1058622 (C4 (Web Text))

Max Activating Token Index: 50

Text #11

Max Range: 1.7958. Min Range: -1.7958

Max Act: 1.1982. Min Act: -0.0000

Data Index: 228948 (C4 (Web Text))

Max Activating Token Index: 75

Text #12

Max Range: 1.7958. Min Range: -1.7958

Max Act: 1.1227. Min Act: -0.0000

Data Index: 128233 (C4 (Web Text))

Max Activating Token Index: 210

Text #13

Max Range: 1.7958. Min Range: -1.7958

Max Act: 1.1949. Min Act: -0.0000

Data Index: 1190958 (C4 (Web Text))

Max Activating Token Index: 417

Text #14

Max Range: 1.7958. Min Range: -1.7958

Max Act: 1.1048. Min Act: -0.0000

Data Index: 961528 (C4 (Web Text))

Max Activating Token Index: 272

Text #15

Max Range: 1.7958. Min Range: -1.7958

Max Act: 1.1698. Min Act: -0.0000

Data Index: 1150024 (C4 (Web Text))

Max Activating Token Index: 543

Text #16

Max Range: 1.7958. Min Range: -1.7958

Max Act: 1.0950. Min Act: -0.0000

Data Index: 965629 (C4 (Web Text))

Max Activating Token Index: 298

Text #17

Max Range: 1.7958. Min Range: -1.7958

Max Act: 1.0384. Min Act: -0.0000

Data Index: 890853 (C4 (Web Text))

Max Activating Token Index: 226

Text #18

Max Range: 1.7958. Min Range: -1.7958

Max Act: 1.0817. Min Act: -0.0000

Data Index: 900502 (C4 (Web Text))

Max Activating Token Index: 421

Text #19

Max Range: 1.7958. Min Range: -1.7958

Max Act: 1.0047. Min Act: -0.0000

Data Index: 876001 (C4 (Web Text))

Max Activating Token Index: 774