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

Dataset: The Pile

Neuron 4399 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: 1.2860. Min Range: -1.2860

Max Act: 1.2407. Min Act: -0.0000

Data Index: 1083626 (The Pile)

Max Activating Token Index: 141

Text #1

Max Range: 1.2860. Min Range: -1.2860

Max Act: 1.2377. Min Act: -0.0000

Data Index: 1206504 (The Pile)

Max Activating Token Index: 47

Text #2

Max Range: 1.2860. Min Range: -1.2860

Max Act: 1.2082. Min Act: -0.0000

Data Index: 1649418 (The Pile)

Max Activating Token Index: 15

Text #3

Max Range: 1.2860. Min Range: -1.2860

Max Act: 1.2805. Min Act: -0.0000

Data Index: 1605172 (The Pile)

Max Activating Token Index: 586

Text #4

Max Range: 1.2860. Min Range: -1.2860

Max Act: 1.2860. Min Act: -0.0000

Data Index: 336566 (The Pile)

Max Activating Token Index: 159

Text #5

Max Range: 1.2860. Min Range: -1.2860

Max Act: 1.1689. Min Act: -0.0000

Data Index: 461874 (The Pile)

Max Activating Token Index: 38

Text #6

Max Range: 1.2860. Min Range: -1.2860

Max Act: 1.1126. Min Act: -0.0000

Data Index: 806162 (The Pile)

Max Activating Token Index: 853

Text #7

Max Range: 1.2860. Min Range: -1.2860

Max Act: 1.1753. Min Act: -0.0000

Data Index: 310030 (The Pile)

Max Activating Token Index: 473

Text #8

Max Range: 1.2860. Min Range: -1.2860

Max Act: 1.0842. Min Act: -0.0000

Data Index: 867887 (The Pile)

Max Activating Token Index: 24

Text #9

Max Range: 1.2860. Min Range: -1.2860

Max Act: 1.0189. Min Act: -0.0000

Data Index: 1627895 (The Pile)

Max Activating Token Index: 190

Text #10

Max Range: 1.2860. Min Range: -1.2860

Max Act: 1.0700. Min Act: -0.0000

Data Index: 837778 (The Pile)

Max Activating Token Index: 581

Text #11

Max Range: 1.2860. Min Range: -1.2860

Max Act: 1.0676. Min Act: -0.0000

Data Index: 1647673 (The Pile)

Max Activating Token Index: 144

Text #12

Max Range: 1.2860. Min Range: -1.2860

Max Act: 1.0204. Min Act: -0.0000

Data Index: 1280628 (The Pile)

Max Activating Token Index: 940

Text #13

Max Range: 1.2860. Min Range: -1.2860

Max Act: 1.0168. Min Act: -0.0000

Data Index: 1972167 (The Pile)

Max Activating Token Index: 504

Text #14

Max Range: 1.2860. Min Range: -1.2860

Max Act: 1.1100. Min Act: -0.0000

Data Index: 432582 (The Pile)

Max Activating Token Index: 226

Text #15

Max Range: 1.2860. Min Range: -1.2860

Max Act: 1.1404. Min Act: -0.0000

Data Index: 383820 (The Pile)

Max Activating Token Index: 852

Text #16

Max Range: 1.2860. Min Range: -1.2860

Max Act: 1.1023. Min Act: -0.0000

Data Index: 1709117 (The Pile)

Max Activating Token Index: 224

Text #17

Max Range: 1.2860. Min Range: -1.2860

Max Act: 0.8975. Min Act: -0.0000

Data Index: 1522521 (The Pile)

Max Activating Token Index: 836

Text #18

Max Range: 1.2860. Min Range: -1.2860

Max Act: 1.0415. Min Act: -0.0000

Data Index: 887220 (The Pile)

Max Activating Token Index: 188

Text #19

Max Range: 1.2860. Min Range: -1.2860

Max Act: 1.0347. Min Act: -0.0000

Data Index: 1482662 (The Pile)

Max Activating Token Index: 262