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

Dataset: The Pile

Neuron 3685 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3263. Min Range: -1.3263

Max Act: 1.3202. Min Act: -0.0000

Data Index: 1502713 (The Pile)

Max Activating Token Index: 595

Text #1

Max Range: 1.3263. Min Range: -1.3263

Max Act: 1.1629. Min Act: -0.0000

Data Index: 305430 (The Pile)

Max Activating Token Index: 302

Text #2

Max Range: 1.3263. Min Range: -1.3263

Max Act: 1.3228. Min Act: -0.0000

Data Index: 307022 (The Pile)

Max Activating Token Index: 942

Text #3

Max Range: 1.3263. Min Range: -1.3263

Max Act: 1.2661. Min Act: -0.0000

Data Index: 782612 (The Pile)

Max Activating Token Index: 158

Text #4

Max Range: 1.3263. Min Range: -1.3263

Max Act: 1.2462. Min Act: -0.0000

Data Index: 1338685 (The Pile)

Max Activating Token Index: 264

Text #5

Max Range: 1.3263. Min Range: -1.3263

Max Act: 1.1545. Min Act: -0.0000

Data Index: 1551914 (The Pile)

Max Activating Token Index: 668

Text #6

Max Range: 1.3263. Min Range: -1.3263

Max Act: 1.3263. Min Act: -0.0000

Data Index: 1633659 (The Pile)

Max Activating Token Index: 459

Text #7

Max Range: 1.3263. Min Range: -1.3263

Max Act: 1.1993. Min Act: -0.0000

Data Index: 725754 (The Pile)

Max Activating Token Index: 128

Text #8

Max Range: 1.3263. Min Range: -1.3263

Max Act: 1.1639. Min Act: -0.0000

Data Index: 386853 (The Pile)

Max Activating Token Index: 128

Text #9

Max Range: 1.3263. Min Range: -1.3263

Max Act: 1.2798. Min Act: -0.0000

Data Index: 1983294 (The Pile)

Max Activating Token Index: 525

Text #10

Max Range: 1.3263. Min Range: -1.3263

Max Act: 1.2630. Min Act: -0.0000

Data Index: 1788506 (The Pile)

Max Activating Token Index: 833

Text #11

Max Range: 1.3263. Min Range: -1.3263

Max Act: 1.1543. Min Act: -0.0000

Data Index: 1346251 (The Pile)

Max Activating Token Index: 348

Text #12

Max Range: 1.3263. Min Range: -1.3263

Max Act: 0.9968. Min Act: -0.0000

Data Index: 1370223 (The Pile)

Max Activating Token Index: 220

Text #13

Max Range: 1.3263. Min Range: -1.3263

Max Act: 1.0961. Min Act: -0.0000

Data Index: 676851 (The Pile)

Max Activating Token Index: 436

Text #14

Max Range: 1.3263. Min Range: -1.3263

Max Act: 1.0262. Min Act: -0.0000

Data Index: 1643462 (The Pile)

Max Activating Token Index: 173

Text #15

Max Range: 1.3263. Min Range: -1.3263

Max Act: 1.0232. Min Act: -0.0000

Data Index: 1954471 (The Pile)

Max Activating Token Index: 402

Text #16

Max Range: 1.3263. Min Range: -1.3263

Max Act: 1.0498. Min Act: -0.0000

Data Index: 932804 (The Pile)

Max Activating Token Index: 823

Text #17

Max Range: 1.3263. Min Range: -1.3263

Max Act: 0.9922. Min Act: -0.0000

Data Index: 1759266 (The Pile)

Max Activating Token Index: 643

Text #18

Max Range: 1.3263. Min Range: -1.3263

Max Act: 0.9717. Min Act: -0.0000

Data Index: 167794 (The Pile)

Max Activating Token Index: 150

Text #19

Max Range: 1.3263. Min Range: -1.3263

Max Act: 1.1111. Min Act: -0.0000

Data Index: 1079881 (The Pile)

Max Activating Token Index: 283