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

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

Neuron 3260 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6139. Min Range: -1.6139

Max Act: 1.6139. Min Act: -0.0000

Data Index: 1198021 (C4 (Web Text))

Max Activating Token Index: 687

Text #1

Max Range: 1.6139. Min Range: -1.6139

Max Act: 1.5978. Min Act: -0.0000

Data Index: 999913 (C4 (Web Text))

Max Activating Token Index: 319

Text #2

Max Range: 1.6139. Min Range: -1.6139

Max Act: 1.5692. Min Act: -0.0000

Data Index: 609753 (C4 (Web Text))

Max Activating Token Index: 736

Text #3

Max Range: 1.6139. Min Range: -1.6139

Max Act: 1.3146. Min Act: -0.0000

Data Index: 436663 (C4 (Web Text))

Max Activating Token Index: 241

Text #4

Max Range: 1.6139. Min Range: -1.6139

Max Act: 1.3113. Min Act: -0.0000

Data Index: 1416331 (Python Code)

Max Activating Token Index: 283

Text #5

Max Range: 1.6139. Min Range: -1.6139

Max Act: 1.5391. Min Act: -0.0000

Data Index: 1330336 (C4 (Web Text))

Max Activating Token Index: 857

Text #6

Max Range: 1.6139. Min Range: -1.6139

Max Act: 1.3310. Min Act: -0.0000

Data Index: 486559 (C4 (Web Text))

Max Activating Token Index: 469

Text #7

Max Range: 1.6139. Min Range: -1.6139

Max Act: 1.3525. Min Act: -0.0000

Data Index: 31641 (C4 (Web Text))

Max Activating Token Index: 700

Text #8

Max Range: 1.6139. Min Range: -1.6139

Max Act: 1.3374. Min Act: -0.0000

Data Index: 1215023 (C4 (Web Text))

Max Activating Token Index: 172

Text #9

Max Range: 1.6139. Min Range: -1.6139

Max Act: 1.3116. Min Act: -0.0000

Data Index: 83282 (C4 (Web Text))

Max Activating Token Index: 626

Text #10

Max Range: 1.6139. Min Range: -1.6139

Max Act: 1.2967. Min Act: -0.0000

Data Index: 412514 (C4 (Web Text))

Max Activating Token Index: 808

Text #11

Max Range: 1.6139. Min Range: -1.6139

Max Act: 1.2121. Min Act: -0.0000

Data Index: 537663 (C4 (Web Text))

Max Activating Token Index: 189

Text #12

Max Range: 1.6139. Min Range: -1.6139

Max Act: 1.4365. Min Act: -0.0000

Data Index: 864602 (C4 (Web Text))

Max Activating Token Index: 193

Text #13

Max Range: 1.6139. Min Range: -1.6139

Max Act: 1.1680. Min Act: -0.0000

Data Index: 147946 (C4 (Web Text))

Max Activating Token Index: 226

Text #14

Max Range: 1.6139. Min Range: -1.6139

Max Act: 1.1544. Min Act: -0.0000

Data Index: 1080405 (C4 (Web Text))

Max Activating Token Index: 879

Text #15

Max Range: 1.6139. Min Range: -1.6139

Max Act: 1.2276. Min Act: -0.0000

Data Index: 214038 (C4 (Web Text))

Max Activating Token Index: 984

Text #16

Max Range: 1.6139. Min Range: -1.6139

Max Act: 1.2218. Min Act: -0.0000

Data Index: 779223 (C4 (Web Text))

Max Activating Token Index: 235

Text #17

Max Range: 1.6139. Min Range: -1.6139

Max Act: 1.2890. Min Act: -0.0000

Data Index: 192109 (C4 (Web Text))

Max Activating Token Index: 896

Text #18

Max Range: 1.6139. Min Range: -1.6139

Max Act: 1.0720. Min Act: -0.0000

Data Index: 771843 (C4 (Web Text))

Max Activating Token Index: 932

Text #19

Max Range: 1.6139. Min Range: -1.6139

Max Act: 1.2817. Min Act: -0.0000

Data Index: 1108078 (C4 (Web Text))

Max Activating Token Index: 706