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

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

Neuron 2895 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.4976. Min Range: -0.4976

Max Act: 0.4976. Min Act: -0.0001

Data Index: 1359066 (C4 (Web Text))

Max Activating Token Index: 212

Text #1

Max Range: 0.4976. Min Range: -0.4976

Max Act: 0.4684. Min Act: -0.0001

Data Index: 630087 (C4 (Web Text))

Max Activating Token Index: 951

Text #2

Max Range: 0.4976. Min Range: -0.4976

Max Act: 0.4920. Min Act: -0.0001

Data Index: 1056115 (C4 (Web Text))

Max Activating Token Index: 888

Text #3

Max Range: 0.4976. Min Range: -0.4976

Max Act: 0.4671. Min Act: -0.0001

Data Index: 133974 (C4 (Web Text))

Max Activating Token Index: 25

Text #4

Max Range: 0.4976. Min Range: -0.4976

Max Act: 0.4685. Min Act: -0.0001

Data Index: 618834 (C4 (Web Text))

Max Activating Token Index: 194

Text #5

Max Range: 0.4976. Min Range: -0.4976

Max Act: 0.4417. Min Act: -0.0001

Data Index: 37817 (C4 (Web Text))

Max Activating Token Index: 743

Text #6

Max Range: 0.4976. Min Range: -0.4976

Max Act: 0.4635. Min Act: -0.0001

Data Index: 237552 (C4 (Web Text))

Max Activating Token Index: 868

Text #7

Max Range: 0.4976. Min Range: -0.4976

Max Act: 0.4295. Min Act: -0.0001

Data Index: 272902 (C4 (Web Text))

Max Activating Token Index: 178

Text #8

Max Range: 0.4976. Min Range: -0.4976

Max Act: 0.4363. Min Act: -0.0001

Data Index: 521736 (C4 (Web Text))

Max Activating Token Index: 174

Text #9

Max Range: 0.4976. Min Range: -0.4976

Max Act: 0.4353. Min Act: -0.0001

Data Index: 868200 (C4 (Web Text))

Max Activating Token Index: 811

Text #10

Max Range: 0.4976. Min Range: -0.4976

Max Act: 0.4433. Min Act: -0.0001

Data Index: 326265 (C4 (Web Text))

Max Activating Token Index: 742

Text #11

Max Range: 0.4976. Min Range: -0.4976

Max Act: 0.4145. Min Act: -0.0001

Data Index: 679561 (C4 (Web Text))

Max Activating Token Index: 119

Text #12

Max Range: 0.4976. Min Range: -0.4976

Max Act: 0.4118. Min Act: -0.0001

Data Index: 133670 (C4 (Web Text))

Max Activating Token Index: 86

Text #13

Max Range: 0.4976. Min Range: -0.4976

Max Act: 0.4085. Min Act: -0.0001

Data Index: 1283632 (C4 (Web Text))

Max Activating Token Index: 925

Text #14

Max Range: 0.4976. Min Range: -0.4976

Max Act: 0.4191. Min Act: -0.0001

Data Index: 645543 (C4 (Web Text))

Max Activating Token Index: 960

Text #15

Max Range: 0.4976. Min Range: -0.4976

Max Act: 0.4195. Min Act: -0.0001

Data Index: 590166 (C4 (Web Text))

Max Activating Token Index: 269

Text #16

Max Range: 0.4976. Min Range: -0.4976

Max Act: 0.4127. Min Act: -0.0001

Data Index: 1225605 (C4 (Web Text))

Max Activating Token Index: 676

Text #17

Max Range: 0.4976. Min Range: -0.4976

Max Act: 0.4049. Min Act: -0.0001

Data Index: 53577 (C4 (Web Text))

Max Activating Token Index: 71

Text #18

Max Range: 0.4976. Min Range: -0.4976

Max Act: 0.4274. Min Act: -0.0001

Data Index: 493619 (C4 (Web Text))

Max Activating Token Index: 22

Text #19

Max Range: 0.4976. Min Range: -0.4976

Max Act: 0.4270. Min Act: -0.0001

Data Index: 938251 (C4 (Web Text))

Max Activating Token Index: 646