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

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

Neuron 4838 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9180. Min Range: -2.9180

Max Act: 2.9180. Min Act: -0.0000

Data Index: 1065628 (C4 (Web Text))

Max Activating Token Index: 528

Text #1

Max Range: 2.9180. Min Range: -2.9180

Max Act: 2.6913. Min Act: -0.0000

Data Index: 274794 (C4 (Web Text))

Max Activating Token Index: 126

Text #2

Max Range: 2.9180. Min Range: -2.9180

Max Act: 2.5261. Min Act: -0.0000

Data Index: 309889 (C4 (Web Text))

Max Activating Token Index: 555

Text #3

Max Range: 2.9180. Min Range: -2.9180

Max Act: 2.2058. Min Act: -0.0000

Data Index: 912043 (C4 (Web Text))

Max Activating Token Index: 779

Text #4

Max Range: 2.9180. Min Range: -2.9180

Max Act: 2.1597. Min Act: -0.0000

Data Index: 1196467 (C4 (Web Text))

Max Activating Token Index: 764

Text #5

Max Range: 2.9180. Min Range: -2.9180

Max Act: 2.3569. Min Act: -0.0000

Data Index: 504457 (C4 (Web Text))

Max Activating Token Index: 980

Text #6

Max Range: 2.9180. Min Range: -2.9180

Max Act: 1.9353. Min Act: -0.0000

Data Index: 330015 (C4 (Web Text))

Max Activating Token Index: 755

Text #7

Max Range: 2.9180. Min Range: -2.9180

Max Act: 2.1951. Min Act: -0.0000

Data Index: 13858 (C4 (Web Text))

Max Activating Token Index: 717

Text #8

Max Range: 2.9180. Min Range: -2.9180

Max Act: 2.0692. Min Act: -0.0000

Data Index: 437264 (C4 (Web Text))

Max Activating Token Index: 936

Text #9

Max Range: 2.9180. Min Range: -2.9180

Max Act: 2.0647. Min Act: -0.0000

Data Index: 302426 (C4 (Web Text))

Max Activating Token Index: 853

Text #10

Max Range: 2.9180. Min Range: -2.9180

Max Act: 1.9166. Min Act: -0.0000

Data Index: 532034 (C4 (Web Text))

Max Activating Token Index: 593

Text #11

Max Range: 2.9180. Min Range: -2.9180

Max Act: 1.9279. Min Act: -0.0000

Data Index: 1051311 (C4 (Web Text))

Max Activating Token Index: 119

Text #12

Max Range: 2.9180. Min Range: -2.9180

Max Act: 1.8880. Min Act: -0.0000

Data Index: 84611 (C4 (Web Text))

Max Activating Token Index: 333

Text #13

Max Range: 2.9180. Min Range: -2.9180

Max Act: 1.7742. Min Act: -0.0000

Data Index: 1058445 (C4 (Web Text))

Max Activating Token Index: 724

Text #14

Max Range: 2.9180. Min Range: -2.9180

Max Act: 1.8510. Min Act: -0.0000

Data Index: 492439 (C4 (Web Text))

Max Activating Token Index: 102

Text #15

Max Range: 2.9180. Min Range: -2.9180

Max Act: 1.8363. Min Act: -0.0000

Data Index: 324816 (C4 (Web Text))

Max Activating Token Index: 400

Text #16

Max Range: 2.9180. Min Range: -2.9180

Max Act: 1.8356. Min Act: -0.0000

Data Index: 681959 (C4 (Web Text))

Max Activating Token Index: 831

Text #17

Max Range: 2.9180. Min Range: -2.9180

Max Act: 1.8120. Min Act: -0.0000

Data Index: 687877 (C4 (Web Text))

Max Activating Token Index: 190

Text #18

Max Range: 2.9180. Min Range: -2.9180

Max Act: 1.8184. Min Act: -0.0000

Data Index: 182639 (C4 (Web Text))

Max Activating Token Index: 231

Text #19

Max Range: 2.9180. Min Range: -2.9180

Max Act: 1.7022. Min Act: -0.0000

Data Index: 1225299 (C4 (Web Text))

Max Activating Token Index: 467