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

Dataset: The Pile

Neuron 3671 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: 7.2496. Min Range: -7.2496

Max Act: 7.2496. Min Act: -0.0000

Data Index: 918993 (The Pile)

Max Activating Token Index: 48

Text #1

Max Range: 7.2496. Min Range: -7.2496

Max Act: 6.6815. Min Act: -0.0000

Data Index: 459554 (The Pile)

Max Activating Token Index: 151

Text #2

Max Range: 7.2496. Min Range: -7.2496

Max Act: 6.2942. Min Act: -0.0000

Data Index: 1113962 (The Pile)

Max Activating Token Index: 93

Text #3

Max Range: 7.2496. Min Range: -7.2496

Max Act: 6.3420. Min Act: -0.0000

Data Index: 709848 (The Pile)

Max Activating Token Index: 39

Text #4

Max Range: 7.2496. Min Range: -7.2496

Max Act: 5.8864. Min Act: -0.0000

Data Index: 1729813 (The Pile)

Max Activating Token Index: 55

Text #5

Max Range: 7.2496. Min Range: -7.2496

Max Act: 6.2451. Min Act: -0.0000

Data Index: 95933 (The Pile)

Max Activating Token Index: 46

Text #6

Max Range: 7.2496. Min Range: -7.2496

Max Act: 6.0362. Min Act: -0.0000

Data Index: 1844406 (The Pile)

Max Activating Token Index: 756

Text #7

Max Range: 7.2496. Min Range: -7.2496

Max Act: 6.0201. Min Act: -0.0000

Data Index: 1987880 (The Pile)

Max Activating Token Index: 47

Text #8

Max Range: 7.2496. Min Range: -7.2496

Max Act: 6.0023. Min Act: -0.0000

Data Index: 517461 (The Pile)

Max Activating Token Index: 81

Text #9

Max Range: 7.2496. Min Range: -7.2496

Max Act: 5.9833. Min Act: -0.0000

Data Index: 1487335 (The Pile)

Max Activating Token Index: 45

Text #10

Max Range: 7.2496. Min Range: -7.2496

Max Act: 6.1267. Min Act: -0.0000

Data Index: 102279 (The Pile)

Max Activating Token Index: 51

Text #11

Max Range: 7.2496. Min Range: -7.2496

Max Act: 5.7354. Min Act: -0.0000

Data Index: 1820190 (The Pile)

Max Activating Token Index: 91

Text #12

Max Range: 7.2496. Min Range: -7.2496

Max Act: 5.9520. Min Act: -0.0000

Data Index: 1177545 (The Pile)

Max Activating Token Index: 178

Text #13

Max Range: 7.2496. Min Range: -7.2496

Max Act: 5.8929. Min Act: -0.0000

Data Index: 960246 (The Pile)

Max Activating Token Index: 44

Text #14

Max Range: 7.2496. Min Range: -7.2496

Max Act: 5.4817. Min Act: -0.0000

Data Index: 1190038 (The Pile)

Max Activating Token Index: 39

Text #15

Max Range: 7.2496. Min Range: -7.2496

Max Act: 6.1790. Min Act: -0.0000

Data Index: 1609858 (The Pile)

Max Activating Token Index: 70

Text #16

Max Range: 7.2496. Min Range: -7.2496

Max Act: 5.8148. Min Act: -0.0000

Data Index: 1167102 (The Pile)

Max Activating Token Index: 789

Text #17

Max Range: 7.2496. Min Range: -7.2496

Max Act: 5.8675. Min Act: -0.0000

Data Index: 509792 (The Pile)

Max Activating Token Index: 158

Text #18

Max Range: 7.2496. Min Range: -7.2496

Max Act: 5.6043. Min Act: -0.0000

Data Index: 1412691 (The Pile)

Max Activating Token Index: 49

Text #19

Max Range: 7.2496. Min Range: -7.2496

Max Act: 5.4112. Min Act: -0.0000

Data Index: 1278944 (The Pile)

Max Activating Token Index: 42