Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1416 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 3.8292. Min Range: -3.8292

Max Act: 3.8292. Min Act: -0.0000

Data Index: 1515300 (The Pile)

Max Activating Token Index: 82

Text #1

Max Range: 3.8292. Min Range: -3.8292

Max Act: 3.6261. Min Act: -0.0000

Data Index: 1141349 (The Pile)

Max Activating Token Index: 609

Text #2

Max Range: 3.8292. Min Range: -3.8292

Max Act: 3.4616. Min Act: -0.0000

Data Index: 805396 (The Pile)

Max Activating Token Index: 350

Text #3

Max Range: 3.8292. Min Range: -3.8292

Max Act: 3.4497. Min Act: -0.0000

Data Index: 1532071 (The Pile)

Max Activating Token Index: 220

Text #4

Max Range: 3.8292. Min Range: -3.8292

Max Act: 3.2257. Min Act: -0.0000

Data Index: 1476100 (The Pile)

Max Activating Token Index: 491

Text #5

Max Range: 3.8292. Min Range: -3.8292

Max Act: 3.7397. Min Act: -0.0000

Data Index: 315727 (The Pile)

Max Activating Token Index: 82

Text #6

Max Range: 3.8292. Min Range: -3.8292

Max Act: 3.4041. Min Act: -0.0000

Data Index: 641615 (The Pile)

Max Activating Token Index: 135

Text #7

Max Range: 3.8292. Min Range: -3.8292

Max Act: 3.6134. Min Act: -0.0000

Data Index: 1899928 (The Pile)

Max Activating Token Index: 326

Text #8

Max Range: 3.8292. Min Range: -3.8292

Max Act: 3.0125. Min Act: -0.0000

Data Index: 265925 (The Pile)

Max Activating Token Index: 137

Text #9

Max Range: 3.8292. Min Range: -3.8292

Max Act: 3.0371. Min Act: -0.0000

Data Index: 355309 (The Pile)

Max Activating Token Index: 61

Text #10

Max Range: 3.8292. Min Range: -3.8292

Max Act: 2.9041. Min Act: -0.0000

Data Index: 1213954 (The Pile)

Max Activating Token Index: 163

Text #11

Max Range: 3.8292. Min Range: -3.8292

Max Act: 2.8897. Min Act: -0.0000

Data Index: 1634826 (The Pile)

Max Activating Token Index: 485

Text #12

Max Range: 3.8292. Min Range: -3.8292

Max Act: 2.7180. Min Act: -0.0000

Data Index: 1225139 (The Pile)

Max Activating Token Index: 212

Text #13

Max Range: 3.8292. Min Range: -3.8292

Max Act: 2.9501. Min Act: -0.0000

Data Index: 1871773 (The Pile)

Max Activating Token Index: 117

Text #14

Max Range: 3.8292. Min Range: -3.8292

Max Act: 2.4201. Min Act: -0.0000

Data Index: 1709102 (The Pile)

Max Activating Token Index: 94

Text #15

Max Range: 3.8292. Min Range: -3.8292

Max Act: 2.7517. Min Act: -0.0000

Data Index: 1085150 (The Pile)

Max Activating Token Index: 314

Text #16

Max Range: 3.8292. Min Range: -3.8292

Max Act: 2.3572. Min Act: -0.0000

Data Index: 1283831 (The Pile)

Max Activating Token Index: 125

Text #17

Max Range: 3.8292. Min Range: -3.8292

Max Act: 2.5869. Min Act: -0.0000

Data Index: 1553001 (The Pile)

Max Activating Token Index: 199

Text #18

Max Range: 3.8292. Min Range: -3.8292

Max Act: 2.5986. Min Act: -0.0000

Data Index: 583890 (The Pile)

Max Activating Token Index: 271

Text #19

Max Range: 3.8292. Min Range: -3.8292

Max Act: 2.2759. Min Act: -0.0000

Data Index: 1728425 (The Pile)

Max Activating Token Index: 568