Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4039 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 5.1798. Min Range: -5.1798

Max Act: 5.1798. Min Act: -0.0000

Data Index: 1023492 (C4 (Web Text))

Max Activating Token Index: 428

Text #1

Max Range: 5.1798. Min Range: -5.1798

Max Act: 4.3664. Min Act: -0.0000

Data Index: 1330928 (C4 (Web Text))

Max Activating Token Index: 34

Text #2

Max Range: 5.1798. Min Range: -5.1798

Max Act: 3.4690. Min Act: -0.0000

Data Index: 595273 (C4 (Web Text))

Max Activating Token Index: 773

Text #3

Max Range: 5.1798. Min Range: -5.1798

Max Act: 3.8379. Min Act: -0.0000

Data Index: 331284 (C4 (Web Text))

Max Activating Token Index: 884

Text #4

Max Range: 5.1798. Min Range: -5.1798

Max Act: 3.5067. Min Act: -0.0000

Data Index: 1159924 (C4 (Web Text))

Max Activating Token Index: 10

Text #5

Max Range: 5.1798. Min Range: -5.1798

Max Act: 3.7768. Min Act: -0.0000

Data Index: 289755 (C4 (Web Text))

Max Activating Token Index: 496

Text #6

Max Range: 5.1798. Min Range: -5.1798

Max Act: 3.3831. Min Act: -0.0000

Data Index: 1322069 (C4 (Web Text))

Max Activating Token Index: 18

Text #7

Max Range: 5.1798. Min Range: -5.1798

Max Act: 3.3813. Min Act: -0.0000

Data Index: 1261844 (C4 (Web Text))

Max Activating Token Index: 618

Text #8

Max Range: 5.1798. Min Range: -5.1798

Max Act: 3.3582. Min Act: -0.0000

Data Index: 382350 (C4 (Web Text))

Max Activating Token Index: 856

Text #9

Max Range: 5.1798. Min Range: -5.1798

Max Act: 3.1921. Min Act: -0.0000

Data Index: 693795 (C4 (Web Text))

Max Activating Token Index: 164

Text #10

Max Range: 5.1798. Min Range: -5.1798

Max Act: 3.1392. Min Act: -0.0000

Data Index: 1076223 (C4 (Web Text))

Max Activating Token Index: 227

Text #11

Max Range: 5.1798. Min Range: -5.1798

Max Act: 3.2707. Min Act: -0.0000

Data Index: 139050 (C4 (Web Text))

Max Activating Token Index: 44

Text #12

Max Range: 5.1798. Min Range: -5.1798

Max Act: 3.0924. Min Act: -0.0000

Data Index: 1149630 (C4 (Web Text))

Max Activating Token Index: 247

Text #13

Max Range: 5.1798. Min Range: -5.1798

Max Act: 3.3715. Min Act: -0.0000

Data Index: 761391 (C4 (Web Text))

Max Activating Token Index: 332

Text #14

Max Range: 5.1798. Min Range: -5.1798

Max Act: 3.1673. Min Act: -0.0000

Data Index: 657835 (C4 (Web Text))

Max Activating Token Index: 555

Text #15

Max Range: 5.1798. Min Range: -5.1798

Max Act: 2.8451. Min Act: -0.0000

Data Index: 695613 (C4 (Web Text))

Max Activating Token Index: 168

Text #16

Max Range: 5.1798. Min Range: -5.1798

Max Act: 3.1482. Min Act: -0.0000

Data Index: 934118 (C4 (Web Text))

Max Activating Token Index: 32

Text #17

Max Range: 5.1798. Min Range: -5.1798

Max Act: 3.0981. Min Act: -0.0000

Data Index: 872759 (C4 (Web Text))

Max Activating Token Index: 551

Text #18

Max Range: 5.1798. Min Range: -5.1798

Max Act: 3.2242. Min Act: -0.0000

Data Index: 38037 (C4 (Web Text))

Max Activating Token Index: 41

Text #19

Max Range: 5.1798. Min Range: -5.1798

Max Act: 3.3612. Min Act: -0.0000

Data Index: 856902 (C4 (Web Text))

Max Activating Token Index: 97