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

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

Neuron 4595 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8550. Min Range: -0.8550

Max Act: 0.8550. Min Act: -0.0000

Data Index: 276507 (C4 (Web Text))

Max Activating Token Index: 305

Text #1

Max Range: 0.8550. Min Range: -0.8550

Max Act: 0.7696. Min Act: -0.0000

Data Index: 698934 (C4 (Web Text))

Max Activating Token Index: 879

Text #2

Max Range: 0.8550. Min Range: -0.8550

Max Act: 0.6985. Min Act: -0.0000

Data Index: 519443 (C4 (Web Text))

Max Activating Token Index: 746

Text #3

Max Range: 0.8550. Min Range: -0.8550

Max Act: 0.6929. Min Act: -0.0000

Data Index: 500247 (C4 (Web Text))

Max Activating Token Index: 540

Text #4

Max Range: 0.8550. Min Range: -0.8550

Max Act: 0.6797. Min Act: -0.0000

Data Index: 1216694 (C4 (Web Text))

Max Activating Token Index: 772

Text #5

Max Range: 0.8550. Min Range: -0.8550

Max Act: 0.6010. Min Act: -0.0000

Data Index: 1138211 (C4 (Web Text))

Max Activating Token Index: 709

Text #6

Max Range: 0.8550. Min Range: -0.8550

Max Act: 0.5640. Min Act: -0.0000

Data Index: 55814 (C4 (Web Text))

Max Activating Token Index: 891

Text #7

Max Range: 0.8550. Min Range: -0.8550

Max Act: 0.5780. Min Act: -0.0000

Data Index: 1222858 (C4 (Web Text))

Max Activating Token Index: 275

Text #8

Max Range: 0.8550. Min Range: -0.8550

Max Act: 0.6072. Min Act: -0.0000

Data Index: 616361 (C4 (Web Text))

Max Activating Token Index: 773

Text #9

Max Range: 0.8550. Min Range: -0.8550

Max Act: 0.5686. Min Act: -0.0000

Data Index: 1262436 (C4 (Web Text))

Max Activating Token Index: 295

Text #10

Max Range: 0.8550. Min Range: -0.8550

Max Act: 0.5820. Min Act: -0.0000

Data Index: 81830 (C4 (Web Text))

Max Activating Token Index: 972

Text #11

Max Range: 0.8550. Min Range: -0.8550

Max Act: 0.5410. Min Act: -0.0000

Data Index: 1342367 (C4 (Web Text))

Max Activating Token Index: 183

Text #12

Max Range: 0.8550. Min Range: -0.8550

Max Act: 0.5249. Min Act: -0.0000

Data Index: 560984 (C4 (Web Text))

Max Activating Token Index: 239

Text #13

Max Range: 0.8550. Min Range: -0.8550

Max Act: 0.5457. Min Act: -0.0000

Data Index: 559214 (C4 (Web Text))

Max Activating Token Index: 188

Text #14

Max Range: 0.8550. Min Range: -0.8550

Max Act: 0.5241. Min Act: -0.0000

Data Index: 946797 (C4 (Web Text))

Max Activating Token Index: 433

Text #15

Max Range: 0.8550. Min Range: -0.8550

Max Act: 0.5433. Min Act: -0.0000

Data Index: 420917 (C4 (Web Text))

Max Activating Token Index: 966

Text #16

Max Range: 0.8550. Min Range: -0.8550

Max Act: 0.5142. Min Act: -0.0000

Data Index: 92180 (C4 (Web Text))

Max Activating Token Index: 994

Text #17

Max Range: 0.8550. Min Range: -0.8550

Max Act: 0.5534. Min Act: -0.0000

Data Index: 207046 (C4 (Web Text))

Max Activating Token Index: 985

Text #18

Max Range: 0.8550. Min Range: -0.8550

Max Act: 0.5079. Min Act: -0.0000

Data Index: 15453 (C4 (Web Text))

Max Activating Token Index: 465

Text #19

Max Range: 0.8550. Min Range: -0.8550

Max Act: 0.5363. Min Act: -0.0000

Data Index: 489795 (C4 (Web Text))

Max Activating Token Index: 40