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

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

Neuron 3176 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: 1.6785. Min Range: -1.6785

Max Act: 1.6785. Min Act: -0.0000

Data Index: 262164 (C4 (Web Text))

Max Activating Token Index: 49

Text #1

Max Range: 1.6785. Min Range: -1.6785

Max Act: 1.4157. Min Act: -0.0000

Data Index: 18102 (C4 (Web Text))

Max Activating Token Index: 952

Text #2

Max Range: 1.6785. Min Range: -1.6785

Max Act: 1.4317. Min Act: -0.0000

Data Index: 1312748 (C4 (Web Text))

Max Activating Token Index: 222

Text #3

Max Range: 1.6785. Min Range: -1.6785

Max Act: 1.3758. Min Act: -0.0000

Data Index: 469519 (C4 (Web Text))

Max Activating Token Index: 119

Text #4

Max Range: 1.6785. Min Range: -1.6785

Max Act: 1.3381. Min Act: -0.0000

Data Index: 1273509 (C4 (Web Text))

Max Activating Token Index: 351

Text #5

Max Range: 1.6785. Min Range: -1.6785

Max Act: 1.3047. Min Act: -0.0000

Data Index: 859643 (C4 (Web Text))

Max Activating Token Index: 241

Text #6

Max Range: 1.6785. Min Range: -1.6785

Max Act: 1.2638. Min Act: -0.0000

Data Index: 1020793 (C4 (Web Text))

Max Activating Token Index: 947

Text #7

Max Range: 1.6785. Min Range: -1.6785

Max Act: 1.2193. Min Act: -0.0000

Data Index: 757741 (C4 (Web Text))

Max Activating Token Index: 1015

Text #8

Max Range: 1.6785. Min Range: -1.6785

Max Act: 1.2186. Min Act: -0.0000

Data Index: 142632 (C4 (Web Text))

Max Activating Token Index: 914

Text #9

Max Range: 1.6785. Min Range: -1.6785

Max Act: 1.1612. Min Act: -0.0000

Data Index: 1012173 (C4 (Web Text))

Max Activating Token Index: 141

Text #10

Max Range: 1.6785. Min Range: -1.6785

Max Act: 1.1691. Min Act: -0.0000

Data Index: 1001223 (C4 (Web Text))

Max Activating Token Index: 827

Text #11

Max Range: 1.6785. Min Range: -1.6785

Max Act: 1.0857. Min Act: -0.0000

Data Index: 569246 (C4 (Web Text))

Max Activating Token Index: 292

Text #12

Max Range: 1.6785. Min Range: -1.6785

Max Act: 1.0880. Min Act: -0.0000

Data Index: 927881 (C4 (Web Text))

Max Activating Token Index: 658

Text #13

Max Range: 1.6785. Min Range: -1.6785

Max Act: 1.1102. Min Act: -0.0000

Data Index: 942578 (C4 (Web Text))

Max Activating Token Index: 94

Text #14

Max Range: 1.6785. Min Range: -1.6785

Max Act: 1.0714. Min Act: -0.0000

Data Index: 1379499 (Python Code)

Max Activating Token Index: 529

Text #15

Max Range: 1.6785. Min Range: -1.6785

Max Act: 1.1277. Min Act: -0.0000

Data Index: 389618 (C4 (Web Text))

Max Activating Token Index: 337

Text #16

Max Range: 1.6785. Min Range: -1.6785

Max Act: 1.0003. Min Act: -0.0000

Data Index: 1212814 (C4 (Web Text))

Max Activating Token Index: 704

Text #17

Max Range: 1.6785. Min Range: -1.6785

Max Act: 1.0200. Min Act: -0.0000

Data Index: 77379 (C4 (Web Text))

Max Activating Token Index: 736

Text #18

Max Range: 1.6785. Min Range: -1.6785

Max Act: 1.0709. Min Act: -0.0000

Data Index: 439666 (C4 (Web Text))

Max Activating Token Index: 510

Text #19

Max Range: 1.6785. Min Range: -1.6785

Max Act: 1.0711. Min Act: -0.0000

Data Index: 478889 (C4 (Web Text))

Max Activating Token Index: 103