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

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

Neuron 1937 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6184. Min Range: -1.6184

Max Act: 1.6184. Min Act: -0.0000

Data Index: 1144977 (C4 (Web Text))

Max Activating Token Index: 1006

Text #1

Max Range: 1.6184. Min Range: -1.6184

Max Act: 1.4586. Min Act: -0.0000

Data Index: 125031 (C4 (Web Text))

Max Activating Token Index: 579

Text #2

Max Range: 1.6184. Min Range: -1.6184

Max Act: 1.2024. Min Act: -0.0000

Data Index: 782804 (C4 (Web Text))

Max Activating Token Index: 218

Text #3

Max Range: 1.6184. Min Range: -1.6184

Max Act: 1.2447. Min Act: -0.0000

Data Index: 169237 (C4 (Web Text))

Max Activating Token Index: 834

Text #4

Max Range: 1.6184. Min Range: -1.6184

Max Act: 1.0799. Min Act: -0.0000

Data Index: 877978 (C4 (Web Text))

Max Activating Token Index: 658

Text #5

Max Range: 1.6184. Min Range: -1.6184

Max Act: 1.2066. Min Act: -0.0000

Data Index: 749074 (C4 (Web Text))

Max Activating Token Index: 1003

Text #6

Max Range: 1.6184. Min Range: -1.6184

Max Act: 1.0764. Min Act: -0.0000

Data Index: 1123147 (C4 (Web Text))

Max Activating Token Index: 927

Text #7

Max Range: 1.6184. Min Range: -1.6184

Max Act: 1.0643. Min Act: -0.0000

Data Index: 1221014 (C4 (Web Text))

Max Activating Token Index: 646

Text #8

Max Range: 1.6184. Min Range: -1.6184

Max Act: 1.0043. Min Act: -0.0000

Data Index: 930096 (C4 (Web Text))

Max Activating Token Index: 307

Text #9

Max Range: 1.6184. Min Range: -1.6184

Max Act: 1.0751. Min Act: -0.0000

Data Index: 252983 (C4 (Web Text))

Max Activating Token Index: 180

Text #10

Max Range: 1.6184. Min Range: -1.6184

Max Act: 1.0264. Min Act: -0.0000

Data Index: 709138 (C4 (Web Text))

Max Activating Token Index: 897

Text #11

Max Range: 1.6184. Min Range: -1.6184

Max Act: 1.0266. Min Act: -0.0000

Data Index: 1550552 (Python Code)

Max Activating Token Index: 639

Text #12

Max Range: 1.6184. Min Range: -1.6184

Max Act: 0.9512. Min Act: -0.0000

Data Index: 558583 (C4 (Web Text))

Max Activating Token Index: 328

Text #13

Max Range: 1.6184. Min Range: -1.6184

Max Act: 0.8558. Min Act: -0.0000

Data Index: 703243 (C4 (Web Text))

Max Activating Token Index: 894

Text #14

Max Range: 1.6184. Min Range: -1.6184

Max Act: 0.9648. Min Act: -0.0000

Data Index: 563681 (C4 (Web Text))

Max Activating Token Index: 105

Text #15

Max Range: 1.6184. Min Range: -1.6184

Max Act: 1.0597. Min Act: -0.0000

Data Index: 271995 (C4 (Web Text))

Max Activating Token Index: 816

Text #16

Max Range: 1.6184. Min Range: -1.6184

Max Act: 0.9542. Min Act: -0.0000

Data Index: 673226 (C4 (Web Text))

Max Activating Token Index: 757

Text #17

Max Range: 1.6184. Min Range: -1.6184

Max Act: 0.8270. Min Act: -0.0000

Data Index: 1205588 (C4 (Web Text))

Max Activating Token Index: 732

Text #18

Max Range: 1.6184. Min Range: -1.6184

Max Act: 0.8831. Min Act: -0.0000

Data Index: 228259 (C4 (Web Text))

Max Activating Token Index: 129

Text #19

Max Range: 1.6184. Min Range: -1.6184

Max Act: 0.9266. Min Act: -0.0000

Data Index: 846643 (C4 (Web Text))

Max Activating Token Index: 194