Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 130 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.9108. Min Range: -0.9108

Max Act: 0.9108. Min Act: -0.0000

Data Index: 618466 (C4 (Web Text))

Max Activating Token Index: 41

Text #1

Max Range: 0.9108. Min Range: -0.9108

Max Act: 0.6174. Min Act: -0.0000

Data Index: 1517178 (Python Code)

Max Activating Token Index: 767

Text #2

Max Range: 0.9108. Min Range: -0.9108

Max Act: 0.5941. Min Act: -0.0000

Data Index: 1451016 (Python Code)

Max Activating Token Index: 178

Text #3

Max Range: 0.9108. Min Range: -0.9108

Max Act: 0.5942. Min Act: 0.0000

Data Index: 1461256 (Python Code)

Max Activating Token Index: 42

Text #4

Max Range: 0.9108. Min Range: -0.9108

Max Act: 0.5890. Min Act: -0.0000

Data Index: 1558320 (Python Code)

Max Activating Token Index: 394

Text #5

Max Range: 0.9108. Min Range: -0.9108

Max Act: 0.5714. Min Act: 0.0001

Data Index: 1655084 (Python Code)

Max Activating Token Index: 733

Text #6

Max Range: 0.9108. Min Range: -0.9108

Max Act: 0.6037. Min Act: -0.0000

Data Index: 404178 (C4 (Web Text))

Max Activating Token Index: 696

Text #7

Max Range: 0.9108. Min Range: -0.9108

Max Act: 0.5712. Min Act: 0.0003

Data Index: 421993 (C4 (Web Text))

Max Activating Token Index: 483

Text #8

Max Range: 0.9108. Min Range: -0.9108

Max Act: 0.5720. Min Act: 0.0000

Data Index: 1552546 (Python Code)

Max Activating Token Index: 561

Text #9

Max Range: 0.9108. Min Range: -0.9108

Max Act: 0.5651. Min Act: 0.0001

Data Index: 1451512 (Python Code)

Max Activating Token Index: 473

Text #10

Max Range: 0.9108. Min Range: -0.9108

Max Act: 0.5558. Min Act: 0.0000

Data Index: 1437339 (Python Code)

Max Activating Token Index: 220

Text #11

Max Range: 0.9108. Min Range: -0.9108

Max Act: 0.5380. Min Act: -0.0000

Data Index: 551609 (C4 (Web Text))

Max Activating Token Index: 37

Text #12

Max Range: 0.9108. Min Range: -0.9108

Max Act: 0.5561. Min Act: 0.0001

Data Index: 1425874 (Python Code)

Max Activating Token Index: 853

Text #13

Max Range: 0.9108. Min Range: -0.9108

Max Act: 0.5219. Min Act: -0.0000

Data Index: 429053 (C4 (Web Text))

Max Activating Token Index: 10

Text #14

Max Range: 0.9108. Min Range: -0.9108

Max Act: 0.5485. Min Act: 0.0001

Data Index: 1377977 (Python Code)

Max Activating Token Index: 291

Text #15

Max Range: 0.9108. Min Range: -0.9108

Max Act: 0.5127. Min Act: -0.0000

Data Index: 1482271 (Python Code)

Max Activating Token Index: 312

Text #16

Max Range: 0.9108. Min Range: -0.9108

Max Act: 0.5074. Min Act: -0.0000

Data Index: 82275 (C4 (Web Text))

Max Activating Token Index: 602

Text #17

Max Range: 0.9108. Min Range: -0.9108

Max Act: 0.5029. Min Act: -0.0000

Data Index: 1576168 (Python Code)

Max Activating Token Index: 272

Text #18

Max Range: 0.9108. Min Range: -0.9108

Max Act: 0.5032. Min Act: -0.0000

Data Index: 1444278 (Python Code)

Max Activating Token Index: 91

Text #19

Max Range: 0.9108. Min Range: -0.9108

Max Act: 0.4888. Min Act: 0.0000

Data Index: 1602897 (Python Code)

Max Activating Token Index: 655