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

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

Neuron 3808 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2055. Min Range: -0.2055

Max Act: 0.2055. Min Act: -0.0000

Data Index: 465568 (C4 (Web Text))

Max Activating Token Index: 107

Text #1

Max Range: 0.2055. Min Range: -0.2055

Max Act: 0.1998. Min Act: -0.0000

Data Index: 399864 (C4 (Web Text))

Max Activating Token Index: 946

Text #2

Max Range: 0.2055. Min Range: -0.2055

Max Act: 0.1866. Min Act: -0.0001

Data Index: 543479 (C4 (Web Text))

Max Activating Token Index: 56

Text #3

Max Range: 0.2055. Min Range: -0.2055

Max Act: 0.1871. Min Act: -0.0001

Data Index: 1570806 (Python Code)

Max Activating Token Index: 745

Text #4

Max Range: 0.2055. Min Range: -0.2055

Max Act: 0.1785. Min Act: -0.0001

Data Index: 1121912 (C4 (Web Text))

Max Activating Token Index: 276

Text #5

Max Range: 0.2055. Min Range: -0.2055

Max Act: 0.1889. Min Act: -0.0000

Data Index: 793196 (C4 (Web Text))

Max Activating Token Index: 282

Text #6

Max Range: 0.2055. Min Range: -0.2055

Max Act: 0.1826. Min Act: -0.0000

Data Index: 410724 (C4 (Web Text))

Max Activating Token Index: 429

Text #7

Max Range: 0.2055. Min Range: -0.2055

Max Act: 0.1771. Min Act: -0.0001

Data Index: 1418115 (Python Code)

Max Activating Token Index: 771

Text #8

Max Range: 0.2055. Min Range: -0.2055

Max Act: 0.1811. Min Act: -0.0001

Data Index: 211726 (C4 (Web Text))

Max Activating Token Index: 473

Text #9

Max Range: 0.2055. Min Range: -0.2055

Max Act: 0.1818. Min Act: -0.0000

Data Index: 1159064 (C4 (Web Text))

Max Activating Token Index: 1020

Text #10

Max Range: 0.2055. Min Range: -0.2055

Max Act: 0.1846. Min Act: -0.0000

Data Index: 572611 (C4 (Web Text))

Max Activating Token Index: 780

Text #11

Max Range: 0.2055. Min Range: -0.2055

Max Act: 0.1776. Min Act: -0.0000

Data Index: 843566 (C4 (Web Text))

Max Activating Token Index: 119

Text #12

Max Range: 0.2055. Min Range: -0.2055

Max Act: 0.1772. Min Act: -0.0000

Data Index: 1031032 (C4 (Web Text))

Max Activating Token Index: 285

Text #13

Max Range: 0.2055. Min Range: -0.2055

Max Act: 0.1699. Min Act: -0.0001

Data Index: 1180584 (C4 (Web Text))

Max Activating Token Index: 309

Text #14

Max Range: 0.2055. Min Range: -0.2055

Max Act: 0.1665. Min Act: -0.0001

Data Index: 1600258 (Python Code)

Max Activating Token Index: 791

Text #15

Max Range: 0.2055. Min Range: -0.2055

Max Act: 0.1732. Min Act: -0.0000

Data Index: 28984 (C4 (Web Text))

Max Activating Token Index: 489

Text #16

Max Range: 0.2055. Min Range: -0.2055

Max Act: 0.1710. Min Act: -0.0001

Data Index: 1616716 (Python Code)

Max Activating Token Index: 303

Text #17

Max Range: 0.2055. Min Range: -0.2055

Max Act: 0.1713. Min Act: -0.0000

Data Index: 1336239 (C4 (Web Text))

Max Activating Token Index: 481

Text #18

Max Range: 0.2055. Min Range: -0.2055

Max Act: 0.1699. Min Act: -0.0001

Data Index: 1394353 (Python Code)

Max Activating Token Index: 145

Text #19

Max Range: 0.2055. Min Range: -0.2055

Max Act: 0.1762. Min Act: -0.0000

Data Index: 1181853 (C4 (Web Text))

Max Activating Token Index: 413