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

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

Neuron 1215 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3837. Min Range: -1.3837

Max Act: 0.0135. Min Act: -0.0000

Data Index: 306641 (C4 (Web Text))

Max Activating Token Index: 915

Text #1

Max Range: 1.3837. Min Range: -1.3837

Max Act: 1.3837. Min Act: -0.0000

Data Index: 1143899 (C4 (Web Text))

Max Activating Token Index: 30

Text #2

Max Range: 1.3837. Min Range: -1.3837

Max Act: 0.3283. Min Act: -0.0000

Data Index: 767408 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 1.3837. Min Range: -1.3837

Max Act: 0.2509. Min Act: -0.0000

Data Index: 1045939 (C4 (Web Text))

Max Activating Token Index: 449

Text #4

Max Range: 1.3837. Min Range: -1.3837

Max Act: 0.1899. Min Act: -0.0000

Data Index: 1151174 (C4 (Web Text))

Max Activating Token Index: 305

Text #5

Max Range: 1.3837. Min Range: -1.3837

Max Act: 0.1421. Min Act: -0.0000

Data Index: 981667 (C4 (Web Text))

Max Activating Token Index: 785

Text #6

Max Range: 1.3837. Min Range: -1.3837

Max Act: 0.1671. Min Act: -0.0000

Data Index: 1185191 (C4 (Web Text))

Max Activating Token Index: 878

Text #7

Max Range: 1.3837. Min Range: -1.3837

Max Act: 0.6691. Min Act: -0.0000

Data Index: 1075823 (C4 (Web Text))

Max Activating Token Index: 978

Text #8

Max Range: 1.3837. Min Range: -1.3837

Max Act: 0.1367. Min Act: -0.0000

Data Index: 12623 (C4 (Web Text))

Max Activating Token Index: 710

Text #9

Max Range: 1.3837. Min Range: -1.3837

Max Act: 0.1391. Min Act: -0.0000

Data Index: 471252 (C4 (Web Text))

Max Activating Token Index: 79

Text #10

Max Range: 1.3837. Min Range: -1.3837

Max Act: 0.1179. Min Act: -0.0000

Data Index: 246103 (C4 (Web Text))

Max Activating Token Index: 327

Text #11

Max Range: 1.3837. Min Range: -1.3837

Max Act: 0.1039. Min Act: -0.0000

Data Index: 310080 (C4 (Web Text))

Max Activating Token Index: 766

Text #12

Max Range: 1.3837. Min Range: -1.3837

Max Act: 0.1503. Min Act: -0.0000

Data Index: 862412 (C4 (Web Text))

Max Activating Token Index: 569

Text #13

Max Range: 1.3837. Min Range: -1.3837

Max Act: 0.1084. Min Act: -0.0000

Data Index: 251515 (C4 (Web Text))

Max Activating Token Index: 665

Text #14

Max Range: 1.3837. Min Range: -1.3837

Max Act: 0.1032. Min Act: -0.0000

Data Index: 328572 (C4 (Web Text))

Max Activating Token Index: 820

Text #15

Max Range: 1.3837. Min Range: -1.3837

Max Act: 0.0978. Min Act: -0.0000

Data Index: 1028190 (C4 (Web Text))

Max Activating Token Index: 681

Text #16

Max Range: 1.3837. Min Range: -1.3837

Max Act: 0.1007. Min Act: -0.0000

Data Index: 1453495 (Python Code)

Max Activating Token Index: 236

Text #17

Max Range: 1.3837. Min Range: -1.3837

Max Act: 0.0963. Min Act: -0.0000

Data Index: 828973 (C4 (Web Text))

Max Activating Token Index: 728

Text #18

Max Range: 1.3837. Min Range: -1.3837

Max Act: 0.0894. Min Act: -0.0000

Data Index: 585467 (C4 (Web Text))

Max Activating Token Index: 966

Text #19

Max Range: 1.3837. Min Range: -1.3837

Max Act: 0.0993. Min Act: -0.0000

Data Index: 336679 (C4 (Web Text))

Max Activating Token Index: 142