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

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

Neuron 2670 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: 7.5194. Min Range: -7.5194

Max Act: 7.3886. Min Act: -0.0000

Data Index: 326541 (C4 (Web Text))

Max Activating Token Index: 892

Text #1

Max Range: 7.5194. Min Range: -7.5194

Max Act: 7.5194. Min Act: -0.0000

Data Index: 461438 (C4 (Web Text))

Max Activating Token Index: 951

Text #2

Max Range: 7.5194. Min Range: -7.5194

Max Act: 6.9712. Min Act: -0.0000

Data Index: 670390 (C4 (Web Text))

Max Activating Token Index: 703

Text #3

Max Range: 7.5194. Min Range: -7.5194

Max Act: 7.0032. Min Act: -0.0000

Data Index: 379141 (C4 (Web Text))

Max Activating Token Index: 670

Text #4

Max Range: 7.5194. Min Range: -7.5194

Max Act: 6.6595. Min Act: -0.0000

Data Index: 287543 (C4 (Web Text))

Max Activating Token Index: 811

Text #5

Max Range: 7.5194. Min Range: -7.5194

Max Act: 6.7773. Min Act: -0.0000

Data Index: 1214282 (C4 (Web Text))

Max Activating Token Index: 795

Text #6

Max Range: 7.5194. Min Range: -7.5194

Max Act: 6.7182. Min Act: -0.0000

Data Index: 146023 (C4 (Web Text))

Max Activating Token Index: 806

Text #7

Max Range: 7.5194. Min Range: -7.5194

Max Act: 6.5077. Min Act: -0.0000

Data Index: 2860 (C4 (Web Text))

Max Activating Token Index: 452

Text #8

Max Range: 7.5194. Min Range: -7.5194

Max Act: 6.8478. Min Act: -0.0000

Data Index: 608956 (C4 (Web Text))

Max Activating Token Index: 309

Text #9

Max Range: 7.5194. Min Range: -7.5194

Max Act: 6.8473. Min Act: -0.0000

Data Index: 1274523 (C4 (Web Text))

Max Activating Token Index: 320

Text #10

Max Range: 7.5194. Min Range: -7.5194

Max Act: 6.6395. Min Act: -0.0000

Data Index: 18957 (C4 (Web Text))

Max Activating Token Index: 658

Text #11

Max Range: 7.5194. Min Range: -7.5194

Max Act: 6.5405. Min Act: -0.0000

Data Index: 901117 (C4 (Web Text))

Max Activating Token Index: 291

Text #12

Max Range: 7.5194. Min Range: -7.5194

Max Act: 6.5459. Min Act: -0.0000

Data Index: 227723 (C4 (Web Text))

Max Activating Token Index: 851

Text #13

Max Range: 7.5194. Min Range: -7.5194

Max Act: 6.5334. Min Act: -0.0000

Data Index: 807891 (C4 (Web Text))

Max Activating Token Index: 133

Text #14

Max Range: 7.5194. Min Range: -7.5194

Max Act: 6.5382. Min Act: -0.0000

Data Index: 561694 (C4 (Web Text))

Max Activating Token Index: 731

Text #15

Max Range: 7.5194. Min Range: -7.5194

Max Act: 6.2106. Min Act: -0.0000

Data Index: 1255946 (C4 (Web Text))

Max Activating Token Index: 703

Text #16

Max Range: 7.5194. Min Range: -7.5194

Max Act: 6.2266. Min Act: -0.0000

Data Index: 864568 (C4 (Web Text))

Max Activating Token Index: 678

Text #17

Max Range: 7.5194. Min Range: -7.5194

Max Act: 6.3614. Min Act: -0.0000

Data Index: 978695 (C4 (Web Text))

Max Activating Token Index: 674

Text #18

Max Range: 7.5194. Min Range: -7.5194

Max Act: 6.1840. Min Act: -0.0000

Data Index: 811523 (C4 (Web Text))

Max Activating Token Index: 58

Text #19

Max Range: 7.5194. Min Range: -7.5194

Max Act: 6.5740. Min Act: -0.0000

Data Index: 331494 (C4 (Web Text))

Max Activating Token Index: 633