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

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

Neuron 5177 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0809. Min Act: -0.0000

Data Index: 127234 (C4 (Web Text))

Max Activating Token Index: 267

Text #1

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0723. Min Act: -0.0000

Data Index: 589319 (C4 (Web Text))

Max Activating Token Index: 290

Text #2

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0713. Min Act: -0.0000

Data Index: 1120719 (C4 (Web Text))

Max Activating Token Index: 254

Text #3

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0653. Min Act: -0.0000

Data Index: 51559 (C4 (Web Text))

Max Activating Token Index: 27

Text #4

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0695. Min Act: -0.0000

Data Index: 435393 (C4 (Web Text))

Max Activating Token Index: 188

Text #5

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0655. Min Act: -0.0000

Data Index: 1199232 (C4 (Web Text))

Max Activating Token Index: 69

Text #6

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0658. Min Act: -0.0000

Data Index: 59229 (C4 (Web Text))

Max Activating Token Index: 197

Text #7

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0650. Min Act: -0.0000

Data Index: 1271735 (C4 (Web Text))

Max Activating Token Index: 46

Text #8

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0647. Min Act: -0.0000

Data Index: 1135362 (C4 (Web Text))

Max Activating Token Index: 461

Text #9

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0645. Min Act: -0.0000

Data Index: 1360161 (Python Code)

Max Activating Token Index: 801

Text #10

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0640. Min Act: -0.0000

Data Index: 238955 (C4 (Web Text))

Max Activating Token Index: 327

Text #11

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0657. Min Act: -0.0000

Data Index: 38997 (C4 (Web Text))

Max Activating Token Index: 279

Text #12

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0622. Min Act: -0.0000

Data Index: 530890 (C4 (Web Text))

Max Activating Token Index: 811

Text #13

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0630. Min Act: -0.0000

Data Index: 1535795 (Python Code)

Max Activating Token Index: 38

Text #14

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0649. Min Act: -0.0000

Data Index: 234843 (C4 (Web Text))

Max Activating Token Index: 498

Text #15

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0622. Min Act: -0.0000

Data Index: 1342311 (C4 (Web Text))

Max Activating Token Index: 911

Text #16

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0667. Min Act: -0.0000

Data Index: 1307029 (C4 (Web Text))

Max Activating Token Index: 945

Text #17

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0576. Min Act: -0.0000

Data Index: 1604027 (Python Code)

Max Activating Token Index: 931

Text #18

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0582. Min Act: -0.0000

Data Index: 1392741 (Python Code)

Max Activating Token Index: 948

Text #19

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0634. Min Act: -0.0000

Data Index: 1312240 (C4 (Web Text))

Max Activating Token Index: 505