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

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

Neuron 4824 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 8.0707. Min Range: -8.0707

Max Act: 8.0707. Min Act: -0.0001

Data Index: 353788 (C4 (Web Text))

Max Activating Token Index: 146

Text #1

Max Range: 8.0707. Min Range: -8.0707

Max Act: 7.6685. Min Act: -0.0001

Data Index: 161046 (C4 (Web Text))

Max Activating Token Index: 952

Text #2

Max Range: 8.0707. Min Range: -8.0707

Max Act: 5.9523. Min Act: -0.0001

Data Index: 826710 (C4 (Web Text))

Max Activating Token Index: 24

Text #3

Max Range: 8.0707. Min Range: -8.0707

Max Act: 6.8487. Min Act: -0.0001

Data Index: 1096600 (C4 (Web Text))

Max Activating Token Index: 600

Text #4

Max Range: 8.0707. Min Range: -8.0707

Max Act: 4.9771. Min Act: -0.0001

Data Index: 272202 (C4 (Web Text))

Max Activating Token Index: 208

Text #5

Max Range: 8.0707. Min Range: -8.0707

Max Act: 5.1884. Min Act: -0.0001

Data Index: 432331 (C4 (Web Text))

Max Activating Token Index: 326

Text #6

Max Range: 8.0707. Min Range: -8.0707

Max Act: 4.9104. Min Act: -0.0001

Data Index: 145324 (C4 (Web Text))

Max Activating Token Index: 807

Text #7

Max Range: 8.0707. Min Range: -8.0707

Max Act: 4.2557. Min Act: -0.0001

Data Index: 903152 (C4 (Web Text))

Max Activating Token Index: 22

Text #8

Max Range: 8.0707. Min Range: -8.0707

Max Act: 4.5733. Min Act: -0.0001

Data Index: 1030698 (C4 (Web Text))

Max Activating Token Index: 605

Text #9

Max Range: 8.0707. Min Range: -8.0707

Max Act: 4.6695. Min Act: -0.0001

Data Index: 602622 (C4 (Web Text))

Max Activating Token Index: 427

Text #10

Max Range: 8.0707. Min Range: -8.0707

Max Act: 4.6424. Min Act: -0.0001

Data Index: 1017746 (C4 (Web Text))

Max Activating Token Index: 217

Text #11

Max Range: 8.0707. Min Range: -8.0707

Max Act: 4.8908. Min Act: -0.0001

Data Index: 96918 (C4 (Web Text))

Max Activating Token Index: 700

Text #12

Max Range: 8.0707. Min Range: -8.0707

Max Act: 4.5701. Min Act: -0.0000

Data Index: 216943 (C4 (Web Text))

Max Activating Token Index: 161

Text #13

Max Range: 8.0707. Min Range: -8.0707

Max Act: 4.0881. Min Act: -0.0001

Data Index: 742447 (C4 (Web Text))

Max Activating Token Index: 234

Text #14

Max Range: 8.0707. Min Range: -8.0707

Max Act: 4.4435. Min Act: -0.0001

Data Index: 657615 (C4 (Web Text))

Max Activating Token Index: 10

Text #15

Max Range: 8.0707. Min Range: -8.0707

Max Act: 5.5098. Min Act: -0.0001

Data Index: 267436 (C4 (Web Text))

Max Activating Token Index: 779

Text #16

Max Range: 8.0707. Min Range: -8.0707

Max Act: 4.2188. Min Act: -0.0001

Data Index: 270942 (C4 (Web Text))

Max Activating Token Index: 136

Text #17

Max Range: 8.0707. Min Range: -8.0707

Max Act: 3.6928. Min Act: -0.0001

Data Index: 14275 (C4 (Web Text))

Max Activating Token Index: 830

Text #18

Max Range: 8.0707. Min Range: -8.0707

Max Act: 4.5198. Min Act: -0.0001

Data Index: 870825 (C4 (Web Text))

Max Activating Token Index: 802

Text #19

Max Range: 8.0707. Min Range: -8.0707

Max Act: 5.0010. Min Act: -0.0001

Data Index: 349469 (C4 (Web Text))

Max Activating Token Index: 877