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

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

Neuron 1733 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8551. Min Range: -1.8551

Max Act: 1.8551. Min Act: -0.0000

Data Index: 599747 (C4 (Web Text))

Max Activating Token Index: 207

Text #1

Max Range: 1.8551. Min Range: -1.8551

Max Act: 1.5860. Min Act: -0.0000

Data Index: 1315130 (C4 (Web Text))

Max Activating Token Index: 626

Text #2

Max Range: 1.8551. Min Range: -1.8551

Max Act: 1.5835. Min Act: -0.0001

Data Index: 269473 (C4 (Web Text))

Max Activating Token Index: 198

Text #3

Max Range: 1.8551. Min Range: -1.8551

Max Act: 1.4141. Min Act: -0.0000

Data Index: 74162 (C4 (Web Text))

Max Activating Token Index: 194

Text #4

Max Range: 1.8551. Min Range: -1.8551

Max Act: 1.5208. Min Act: -0.0001

Data Index: 63177 (C4 (Web Text))

Max Activating Token Index: 324

Text #5

Max Range: 1.8551. Min Range: -1.8551

Max Act: 1.3913. Min Act: -0.0000

Data Index: 110674 (C4 (Web Text))

Max Activating Token Index: 647

Text #6

Max Range: 1.8551. Min Range: -1.8551

Max Act: 1.4541. Min Act: -0.0000

Data Index: 245259 (C4 (Web Text))

Max Activating Token Index: 168

Text #7

Max Range: 1.8551. Min Range: -1.8551

Max Act: 1.3620. Min Act: -0.0000

Data Index: 201084 (C4 (Web Text))

Max Activating Token Index: 388

Text #8

Max Range: 1.8551. Min Range: -1.8551

Max Act: 1.3607. Min Act: -0.0000

Data Index: 987174 (C4 (Web Text))

Max Activating Token Index: 66

Text #9

Max Range: 1.8551. Min Range: -1.8551

Max Act: 1.3549. Min Act: -0.0000

Data Index: 1001666 (C4 (Web Text))

Max Activating Token Index: 32

Text #10

Max Range: 1.8551. Min Range: -1.8551

Max Act: 1.3379. Min Act: -0.0000

Data Index: 1023163 (C4 (Web Text))

Max Activating Token Index: 793

Text #11

Max Range: 1.8551. Min Range: -1.8551

Max Act: 1.3212. Min Act: -0.0000

Data Index: 1233867 (C4 (Web Text))

Max Activating Token Index: 315

Text #12

Max Range: 1.8551. Min Range: -1.8551

Max Act: 1.3286. Min Act: -0.0000

Data Index: 987696 (C4 (Web Text))

Max Activating Token Index: 275

Text #13

Max Range: 1.8551. Min Range: -1.8551

Max Act: 1.3397. Min Act: -0.0000

Data Index: 948664 (C4 (Web Text))

Max Activating Token Index: 788

Text #14

Max Range: 1.8551. Min Range: -1.8551

Max Act: 1.3145. Min Act: -0.0001

Data Index: 1406875 (Python Code)

Max Activating Token Index: 36

Text #15

Max Range: 1.8551. Min Range: -1.8551

Max Act: 1.3219. Min Act: -0.0000

Data Index: 223705 (C4 (Web Text))

Max Activating Token Index: 995

Text #16

Max Range: 1.8551. Min Range: -1.8551

Max Act: 1.2201. Min Act: -0.0001

Data Index: 1191227 (C4 (Web Text))

Max Activating Token Index: 932

Text #17

Max Range: 1.8551. Min Range: -1.8551

Max Act: 1.3576. Min Act: -0.0000

Data Index: 1054803 (C4 (Web Text))

Max Activating Token Index: 697

Text #18

Max Range: 1.8551. Min Range: -1.8551

Max Act: 1.2343. Min Act: -0.0000

Data Index: 297855 (C4 (Web Text))

Max Activating Token Index: 689

Text #19

Max Range: 1.8551. Min Range: -1.8551

Max Act: 1.3474. Min Act: -0.0001

Data Index: 1098936 (C4 (Web Text))

Max Activating Token Index: 480