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

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

Neuron 795 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3829. Min Range: -1.3829

Max Act: 1.3829. Min Act: -0.0000

Data Index: 651274 (C4 (Web Text))

Max Activating Token Index: 229

Text #1

Max Range: 1.3829. Min Range: -1.3829

Max Act: 1.2065. Min Act: -0.0000

Data Index: 581778 (C4 (Web Text))

Max Activating Token Index: 578

Text #2

Max Range: 1.3829. Min Range: -1.3829

Max Act: 1.1465. Min Act: -0.0000

Data Index: 465829 (C4 (Web Text))

Max Activating Token Index: 970

Text #3

Max Range: 1.3829. Min Range: -1.3829

Max Act: 1.0734. Min Act: -0.0000

Data Index: 817187 (C4 (Web Text))

Max Activating Token Index: 502

Text #4

Max Range: 1.3829. Min Range: -1.3829

Max Act: 0.9950. Min Act: -0.0000

Data Index: 741046 (C4 (Web Text))

Max Activating Token Index: 27

Text #5

Max Range: 1.3829. Min Range: -1.3829

Max Act: 1.0550. Min Act: -0.0000

Data Index: 258885 (C4 (Web Text))

Max Activating Token Index: 166

Text #6

Max Range: 1.3829. Min Range: -1.3829

Max Act: 0.9856. Min Act: -0.0000

Data Index: 90164 (C4 (Web Text))

Max Activating Token Index: 222

Text #7

Max Range: 1.3829. Min Range: -1.3829

Max Act: 0.8256. Min Act: -0.0000

Data Index: 636350 (C4 (Web Text))

Max Activating Token Index: 837

Text #8

Max Range: 1.3829. Min Range: -1.3829

Max Act: 0.9395. Min Act: -0.0000

Data Index: 734451 (C4 (Web Text))

Max Activating Token Index: 501

Text #9

Max Range: 1.3829. Min Range: -1.3829

Max Act: 0.9919. Min Act: -0.0000

Data Index: 383980 (C4 (Web Text))

Max Activating Token Index: 134

Text #10

Max Range: 1.3829. Min Range: -1.3829

Max Act: 0.8990. Min Act: -0.0000

Data Index: 1190463 (C4 (Web Text))

Max Activating Token Index: 974

Text #11

Max Range: 1.3829. Min Range: -1.3829

Max Act: 0.8216. Min Act: -0.0000

Data Index: 722577 (C4 (Web Text))

Max Activating Token Index: 764

Text #12

Max Range: 1.3829. Min Range: -1.3829

Max Act: 0.8821. Min Act: -0.0000

Data Index: 1012214 (C4 (Web Text))

Max Activating Token Index: 679

Text #13

Max Range: 1.3829. Min Range: -1.3829

Max Act: 0.8653. Min Act: -0.0000

Data Index: 1296901 (C4 (Web Text))

Max Activating Token Index: 107

Text #14

Max Range: 1.3829. Min Range: -1.3829

Max Act: 0.8347. Min Act: -0.0000

Data Index: 835647 (C4 (Web Text))

Max Activating Token Index: 360

Text #15

Max Range: 1.3829. Min Range: -1.3829

Max Act: 0.8668. Min Act: -0.0000

Data Index: 56002 (C4 (Web Text))

Max Activating Token Index: 267

Text #16

Max Range: 1.3829. Min Range: -1.3829

Max Act: 0.8657. Min Act: -0.0000

Data Index: 389966 (C4 (Web Text))

Max Activating Token Index: 366

Text #17

Max Range: 1.3829. Min Range: -1.3829

Max Act: 0.8874. Min Act: -0.0000

Data Index: 909540 (C4 (Web Text))

Max Activating Token Index: 776

Text #18

Max Range: 1.3829. Min Range: -1.3829

Max Act: 0.8308. Min Act: -0.0000

Data Index: 1065571 (C4 (Web Text))

Max Activating Token Index: 433

Text #19

Max Range: 1.3829. Min Range: -1.3829

Max Act: 0.8447. Min Act: -0.0000

Data Index: 413188 (C4 (Web Text))

Max Activating Token Index: 570