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

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

Neuron 1304 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: 0.6267. Min Range: -0.6267

Max Act: 0.6267. Min Act: -0.0000

Data Index: 1335942 (C4 (Web Text))

Max Activating Token Index: 826

Text #1

Max Range: 0.6267. Min Range: -0.6267

Max Act: 0.5928. Min Act: -0.0000

Data Index: 725376 (C4 (Web Text))

Max Activating Token Index: 399

Text #2

Max Range: 0.6267. Min Range: -0.6267

Max Act: 0.5978. Min Act: -0.0000

Data Index: 351418 (C4 (Web Text))

Max Activating Token Index: 77

Text #3

Max Range: 0.6267. Min Range: -0.6267

Max Act: 0.5333. Min Act: -0.0000

Data Index: 1161084 (C4 (Web Text))

Max Activating Token Index: 856

Text #4

Max Range: 0.6267. Min Range: -0.6267

Max Act: 0.5872. Min Act: -0.0000

Data Index: 763830 (C4 (Web Text))

Max Activating Token Index: 449

Text #5

Max Range: 0.6267. Min Range: -0.6267

Max Act: 0.5631. Min Act: -0.0000

Data Index: 484702 (C4 (Web Text))

Max Activating Token Index: 319

Text #6

Max Range: 0.6267. Min Range: -0.6267

Max Act: 0.5326. Min Act: -0.0001

Data Index: 1211571 (C4 (Web Text))

Max Activating Token Index: 998

Text #7

Max Range: 0.6267. Min Range: -0.6267

Max Act: 0.5544. Min Act: -0.0000

Data Index: 271357 (C4 (Web Text))

Max Activating Token Index: 493

Text #8

Max Range: 0.6267. Min Range: -0.6267

Max Act: 0.5717. Min Act: -0.0000

Data Index: 819327 (C4 (Web Text))

Max Activating Token Index: 996

Text #9

Max Range: 0.6267. Min Range: -0.6267

Max Act: 0.6080. Min Act: -0.0000

Data Index: 392198 (C4 (Web Text))

Max Activating Token Index: 962

Text #10

Max Range: 0.6267. Min Range: -0.6267

Max Act: 0.5801. Min Act: -0.0000

Data Index: 857416 (C4 (Web Text))

Max Activating Token Index: 50

Text #11

Max Range: 0.6267. Min Range: -0.6267

Max Act: 0.5587. Min Act: -0.0000

Data Index: 1011669 (C4 (Web Text))

Max Activating Token Index: 75

Text #12

Max Range: 0.6267. Min Range: -0.6267

Max Act: 0.5968. Min Act: -0.0000

Data Index: 618406 (C4 (Web Text))

Max Activating Token Index: 439

Text #13

Max Range: 0.6267. Min Range: -0.6267

Max Act: 0.5064. Min Act: -0.0000

Data Index: 1024 (C4 (Web Text))

Max Activating Token Index: 882

Text #14

Max Range: 0.6267. Min Range: -0.6267

Max Act: 0.5520. Min Act: -0.0000

Data Index: 88238 (C4 (Web Text))

Max Activating Token Index: 641

Text #15

Max Range: 0.6267. Min Range: -0.6267

Max Act: 0.5477. Min Act: -0.0000

Data Index: 441583 (C4 (Web Text))

Max Activating Token Index: 546

Text #16

Max Range: 0.6267. Min Range: -0.6267

Max Act: 0.5449. Min Act: -0.0000

Data Index: 498627 (C4 (Web Text))

Max Activating Token Index: 190

Text #17

Max Range: 0.6267. Min Range: -0.6267

Max Act: 0.5413. Min Act: -0.0000

Data Index: 661530 (C4 (Web Text))

Max Activating Token Index: 82

Text #18

Max Range: 0.6267. Min Range: -0.6267

Max Act: 0.5539. Min Act: -0.0000

Data Index: 1651499 (Python Code)

Max Activating Token Index: 832

Text #19

Max Range: 0.6267. Min Range: -0.6267

Max Act: 0.5617. Min Act: -0.0000

Data Index: 1253425 (C4 (Web Text))

Max Activating Token Index: 186