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

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

Neuron 4021 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: 0.6813. Min Range: -0.6813

Max Act: 0.6813. Min Act: -0.0000

Data Index: 923808 (C4 (Web Text))

Max Activating Token Index: 899

Text #1

Max Range: 0.6813. Min Range: -0.6813

Max Act: 0.6035. Min Act: -0.0000

Data Index: 496870 (C4 (Web Text))

Max Activating Token Index: 869

Text #2

Max Range: 0.6813. Min Range: -0.6813

Max Act: 0.6169. Min Act: -0.0000

Data Index: 404073 (C4 (Web Text))

Max Activating Token Index: 259

Text #3

Max Range: 0.6813. Min Range: -0.6813

Max Act: 0.5786. Min Act: -0.0000

Data Index: 834183 (C4 (Web Text))

Max Activating Token Index: 781

Text #4

Max Range: 0.6813. Min Range: -0.6813

Max Act: 0.5931. Min Act: -0.0000

Data Index: 711131 (C4 (Web Text))

Max Activating Token Index: 583

Text #5

Max Range: 0.6813. Min Range: -0.6813

Max Act: 0.5689. Min Act: -0.0000

Data Index: 798352 (C4 (Web Text))

Max Activating Token Index: 802

Text #6

Max Range: 0.6813. Min Range: -0.6813

Max Act: 0.5611. Min Act: -0.0000

Data Index: 725209 (C4 (Web Text))

Max Activating Token Index: 738

Text #7

Max Range: 0.6813. Min Range: -0.6813

Max Act: 0.5383. Min Act: -0.0000

Data Index: 1229090 (C4 (Web Text))

Max Activating Token Index: 866

Text #8

Max Range: 0.6813. Min Range: -0.6813

Max Act: 0.5489. Min Act: -0.0000

Data Index: 426727 (C4 (Web Text))

Max Activating Token Index: 899

Text #9

Max Range: 0.6813. Min Range: -0.6813

Max Act: 0.5708. Min Act: -0.0000

Data Index: 552919 (C4 (Web Text))

Max Activating Token Index: 750

Text #10

Max Range: 0.6813. Min Range: -0.6813

Max Act: 0.5307. Min Act: -0.0000

Data Index: 1085158 (C4 (Web Text))

Max Activating Token Index: 252

Text #11

Max Range: 0.6813. Min Range: -0.6813

Max Act: 0.5369. Min Act: -0.0000

Data Index: 374775 (C4 (Web Text))

Max Activating Token Index: 300

Text #12

Max Range: 0.6813. Min Range: -0.6813

Max Act: 0.5372. Min Act: -0.0000

Data Index: 912171 (C4 (Web Text))

Max Activating Token Index: 723

Text #13

Max Range: 0.6813. Min Range: -0.6813

Max Act: 0.5332. Min Act: -0.0000

Data Index: 216766 (C4 (Web Text))

Max Activating Token Index: 891

Text #14

Max Range: 0.6813. Min Range: -0.6813

Max Act: 0.5290. Min Act: -0.0000

Data Index: 228921 (C4 (Web Text))

Max Activating Token Index: 851

Text #15

Max Range: 0.6813. Min Range: -0.6813

Max Act: 0.5056. Min Act: -0.0000

Data Index: 89672 (C4 (Web Text))

Max Activating Token Index: 895

Text #16

Max Range: 0.6813. Min Range: -0.6813

Max Act: 0.5166. Min Act: -0.0000

Data Index: 1340686 (C4 (Web Text))

Max Activating Token Index: 660

Text #17

Max Range: 0.6813. Min Range: -0.6813

Max Act: 0.5304. Min Act: -0.0000

Data Index: 422498 (C4 (Web Text))

Max Activating Token Index: 942

Text #18

Max Range: 0.6813. Min Range: -0.6813

Max Act: 0.5046. Min Act: -0.0000

Data Index: 221867 (C4 (Web Text))

Max Activating Token Index: 161

Text #19

Max Range: 0.6813. Min Range: -0.6813

Max Act: 0.4980. Min Act: -0.0000

Data Index: 62610 (C4 (Web Text))

Max Activating Token Index: 473