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

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

Neuron 3097 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: 0.5850. Min Range: -0.5850

Max Act: 0.5850. Min Act: -0.0000

Data Index: 337680 (C4 (Web Text))

Max Activating Token Index: 532

Text #1

Max Range: 0.5850. Min Range: -0.5850

Max Act: 0.5080. Min Act: -0.0000

Data Index: 860027 (C4 (Web Text))

Max Activating Token Index: 197

Text #2

Max Range: 0.5850. Min Range: -0.5850

Max Act: 0.4713. Min Act: -0.0000

Data Index: 1079402 (C4 (Web Text))

Max Activating Token Index: 895

Text #3

Max Range: 0.5850. Min Range: -0.5850

Max Act: 0.4541. Min Act: -0.0000

Data Index: 547917 (C4 (Web Text))

Max Activating Token Index: 387

Text #4

Max Range: 0.5850. Min Range: -0.5850

Max Act: 0.4499. Min Act: -0.0000

Data Index: 1253181 (C4 (Web Text))

Max Activating Token Index: 503

Text #5

Max Range: 0.5850. Min Range: -0.5850

Max Act: 0.4464. Min Act: 0.0000

Data Index: 1243692 (C4 (Web Text))

Max Activating Token Index: 169

Text #6

Max Range: 0.5850. Min Range: -0.5850

Max Act: 0.4285. Min Act: -0.0001

Data Index: 788385 (C4 (Web Text))

Max Activating Token Index: 432

Text #7

Max Range: 0.5850. Min Range: -0.5850

Max Act: 0.4270. Min Act: -0.0001

Data Index: 483240 (C4 (Web Text))

Max Activating Token Index: 653

Text #8

Max Range: 0.5850. Min Range: -0.5850

Max Act: 0.3860. Min Act: -0.0000

Data Index: 683030 (C4 (Web Text))

Max Activating Token Index: 361

Text #9

Max Range: 0.5850. Min Range: -0.5850

Max Act: 0.4035. Min Act: -0.0000

Data Index: 1214513 (C4 (Web Text))

Max Activating Token Index: 107

Text #10

Max Range: 0.5850. Min Range: -0.5850

Max Act: 0.3792. Min Act: -0.0000

Data Index: 584221 (C4 (Web Text))

Max Activating Token Index: 634

Text #11

Max Range: 0.5850. Min Range: -0.5850

Max Act: 0.4122. Min Act: 0.0000

Data Index: 740372 (C4 (Web Text))

Max Activating Token Index: 45

Text #12

Max Range: 0.5850. Min Range: -0.5850

Max Act: 0.4201. Min Act: -0.0001

Data Index: 76099 (C4 (Web Text))

Max Activating Token Index: 727

Text #13

Max Range: 0.5850. Min Range: -0.5850

Max Act: 0.3767. Min Act: -0.0000

Data Index: 1087232 (C4 (Web Text))

Max Activating Token Index: 881

Text #14

Max Range: 0.5850. Min Range: -0.5850

Max Act: 0.4017. Min Act: -0.0000

Data Index: 782731 (C4 (Web Text))

Max Activating Token Index: 161

Text #15

Max Range: 0.5850. Min Range: -0.5850

Max Act: 0.3739. Min Act: -0.0000

Data Index: 895659 (C4 (Web Text))

Max Activating Token Index: 203

Text #16

Max Range: 0.5850. Min Range: -0.5850

Max Act: 0.3908. Min Act: -0.0000

Data Index: 277945 (C4 (Web Text))

Max Activating Token Index: 331

Text #17

Max Range: 0.5850. Min Range: -0.5850

Max Act: 0.3723. Min Act: 0.0000

Data Index: 1226994 (C4 (Web Text))

Max Activating Token Index: 198

Text #18

Max Range: 0.5850. Min Range: -0.5850

Max Act: 0.3610. Min Act: 0.0000

Data Index: 329522 (C4 (Web Text))

Max Activating Token Index: 976

Text #19

Max Range: 0.5850. Min Range: -0.5850

Max Act: 0.3389. Min Act: 0.0000

Data Index: 877440 (C4 (Web Text))

Max Activating Token Index: 702