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

Dataset: The Pile

Neuron 4990 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8412. Min Range: -0.8412

Max Act: 0.8345. Min Act: -0.0000

Data Index: 85501 (The Pile)

Max Activating Token Index: 744

Text #1

Max Range: 0.8412. Min Range: -0.8412

Max Act: 0.8412. Min Act: -0.0000

Data Index: 1254359 (The Pile)

Max Activating Token Index: 1007

Text #2

Max Range: 0.8412. Min Range: -0.8412

Max Act: 0.7653. Min Act: -0.0000

Data Index: 1547016 (The Pile)

Max Activating Token Index: 668

Text #3

Max Range: 0.8412. Min Range: -0.8412

Max Act: 0.6850. Min Act: -0.0000

Data Index: 1396557 (The Pile)

Max Activating Token Index: 726

Text #4

Max Range: 0.8412. Min Range: -0.8412

Max Act: 0.6234. Min Act: -0.0000

Data Index: 1556039 (The Pile)

Max Activating Token Index: 850

Text #5

Max Range: 0.8412. Min Range: -0.8412

Max Act: 0.6648. Min Act: -0.0000

Data Index: 1280157 (The Pile)

Max Activating Token Index: 350

Text #6

Max Range: 0.8412. Min Range: -0.8412

Max Act: 0.6272. Min Act: -0.0000

Data Index: 406033 (The Pile)

Max Activating Token Index: 696

Text #7

Max Range: 0.8412. Min Range: -0.8412

Max Act: 0.6163. Min Act: -0.0000

Data Index: 797562 (The Pile)

Max Activating Token Index: 258

Text #8

Max Range: 0.8412. Min Range: -0.8412

Max Act: 0.6548. Min Act: -0.0000

Data Index: 368078 (The Pile)

Max Activating Token Index: 63

Text #9

Max Range: 0.8412. Min Range: -0.8412

Max Act: 0.6721. Min Act: -0.0000

Data Index: 599658 (The Pile)

Max Activating Token Index: 699

Text #10

Max Range: 0.8412. Min Range: -0.8412

Max Act: 0.6142. Min Act: -0.0000

Data Index: 1498251 (The Pile)

Max Activating Token Index: 678

Text #11

Max Range: 0.8412. Min Range: -0.8412

Max Act: 0.6970. Min Act: -0.0000

Data Index: 1173972 (The Pile)

Max Activating Token Index: 900

Text #12

Max Range: 0.8412. Min Range: -0.8412

Max Act: 0.5906. Min Act: -0.0000

Data Index: 1635842 (The Pile)

Max Activating Token Index: 786

Text #13

Max Range: 0.8412. Min Range: -0.8412

Max Act: 0.6533. Min Act: -0.0000

Data Index: 133862 (The Pile)

Max Activating Token Index: 809

Text #14

Max Range: 0.8412. Min Range: -0.8412

Max Act: 0.6196. Min Act: -0.0000

Data Index: 190801 (The Pile)

Max Activating Token Index: 159

Text #15

Max Range: 0.8412. Min Range: -0.8412

Max Act: 0.6380. Min Act: -0.0000

Data Index: 1535618 (The Pile)

Max Activating Token Index: 117

Text #16

Max Range: 0.8412. Min Range: -0.8412

Max Act: 0.6145. Min Act: -0.0000

Data Index: 1416998 (The Pile)

Max Activating Token Index: 426

Text #17

Max Range: 0.8412. Min Range: -0.8412

Max Act: 0.5949. Min Act: -0.0000

Data Index: 882852 (The Pile)

Max Activating Token Index: 788

Text #18

Max Range: 0.8412. Min Range: -0.8412

Max Act: 0.5677. Min Act: -0.0000

Data Index: 149049 (The Pile)

Max Activating Token Index: 684

Text #19

Max Range: 0.8412. Min Range: -0.8412

Max Act: 0.6016. Min Act: -0.0000

Data Index: 701099 (The Pile)

Max Activating Token Index: 562