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

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

Neuron 2939 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7801. Min Range: -0.7801

Max Act: 0.7801. Min Act: -0.0001

Data Index: 77925 (C4 (Web Text))

Max Activating Token Index: 990

Text #1

Max Range: 0.7801. Min Range: -0.7801

Max Act: 0.6671. Min Act: -0.0002

Data Index: 875931 (C4 (Web Text))

Max Activating Token Index: 645

Text #2

Max Range: 0.7801. Min Range: -0.7801

Max Act: 0.6305. Min Act: -0.0002

Data Index: 1350070 (C4 (Web Text))

Max Activating Token Index: 942

Text #3

Max Range: 0.7801. Min Range: -0.7801

Max Act: 0.6570. Min Act: -0.0001

Data Index: 844501 (C4 (Web Text))

Max Activating Token Index: 286

Text #4

Max Range: 0.7801. Min Range: -0.7801

Max Act: 0.6191. Min Act: -0.0002

Data Index: 196782 (C4 (Web Text))

Max Activating Token Index: 3

Text #5

Max Range: 0.7801. Min Range: -0.7801

Max Act: 0.6122. Min Act: -0.0001

Data Index: 1152121 (C4 (Web Text))

Max Activating Token Index: 4

Text #6

Max Range: 0.7801. Min Range: -0.7801

Max Act: 0.5638. Min Act: -0.0001

Data Index: 528537 (C4 (Web Text))

Max Activating Token Index: 803

Text #7

Max Range: 0.7801. Min Range: -0.7801

Max Act: 0.6149. Min Act: -0.0001

Data Index: 76729 (C4 (Web Text))

Max Activating Token Index: 943

Text #8

Max Range: 0.7801. Min Range: -0.7801

Max Act: 0.6033. Min Act: -0.0002

Data Index: 63174 (C4 (Web Text))

Max Activating Token Index: 803

Text #9

Max Range: 0.7801. Min Range: -0.7801

Max Act: 0.6152. Min Act: -0.0001

Data Index: 89893 (C4 (Web Text))

Max Activating Token Index: 911

Text #10

Max Range: 0.7801. Min Range: -0.7801

Max Act: 0.6322. Min Act: -0.0002

Data Index: 613817 (C4 (Web Text))

Max Activating Token Index: 954

Text #11

Max Range: 0.7801. Min Range: -0.7801

Max Act: 0.6556. Min Act: -0.0001

Data Index: 988559 (C4 (Web Text))

Max Activating Token Index: 297

Text #12

Max Range: 0.7801. Min Range: -0.7801

Max Act: 0.6231. Min Act: -0.0001

Data Index: 1334505 (C4 (Web Text))

Max Activating Token Index: 18

Text #13

Max Range: 0.7801. Min Range: -0.7801

Max Act: 0.5790. Min Act: -0.0002

Data Index: 312311 (C4 (Web Text))

Max Activating Token Index: 160

Text #14

Max Range: 0.7801. Min Range: -0.7801

Max Act: 0.5578. Min Act: -0.0002

Data Index: 536322 (C4 (Web Text))

Max Activating Token Index: 1006

Text #15

Max Range: 0.7801. Min Range: -0.7801

Max Act: 0.5607. Min Act: -0.0002

Data Index: 1225113 (C4 (Web Text))

Max Activating Token Index: 684

Text #16

Max Range: 0.7801. Min Range: -0.7801

Max Act: 0.5760. Min Act: -0.0002

Data Index: 250249 (C4 (Web Text))

Max Activating Token Index: 161

Text #17

Max Range: 0.7801. Min Range: -0.7801

Max Act: 0.5926. Min Act: -0.0001

Data Index: 618425 (C4 (Web Text))

Max Activating Token Index: 475

Text #18

Max Range: 0.7801. Min Range: -0.7801

Max Act: 0.5723. Min Act: -0.0001

Data Index: 198510 (C4 (Web Text))

Max Activating Token Index: 717

Text #19

Max Range: 0.7801. Min Range: -0.7801

Max Act: 0.6123. Min Act: -0.0002

Data Index: 21350 (C4 (Web Text))

Max Activating Token Index: 399