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

Dataset: The Pile

Neuron 1595 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9410. Min Range: -1.9410

Max Act: 1.9410. Min Act: -0.0000

Data Index: 181438 (The Pile)

Max Activating Token Index: 234

Text #1

Max Range: 1.9410. Min Range: -1.9410

Max Act: 1.6080. Min Act: -0.0000

Data Index: 1773091 (The Pile)

Max Activating Token Index: 980

Text #2

Max Range: 1.9410. Min Range: -1.9410

Max Act: 1.5733. Min Act: -0.0000

Data Index: 1835543 (The Pile)

Max Activating Token Index: 311

Text #3

Max Range: 1.9410. Min Range: -1.9410

Max Act: 1.4584. Min Act: -0.0000

Data Index: 839634 (The Pile)

Max Activating Token Index: 37

Text #4

Max Range: 1.9410. Min Range: -1.9410

Max Act: 1.3936. Min Act: -0.0000

Data Index: 1030095 (The Pile)

Max Activating Token Index: 738

Text #5

Max Range: 1.9410. Min Range: -1.9410

Max Act: 1.3585. Min Act: -0.0000

Data Index: 1849560 (The Pile)

Max Activating Token Index: 298

Text #6

Max Range: 1.9410. Min Range: -1.9410

Max Act: 1.4174. Min Act: -0.0000

Data Index: 1928652 (The Pile)

Max Activating Token Index: 184

Text #7

Max Range: 1.9410. Min Range: -1.9410

Max Act: 1.4045. Min Act: -0.0000

Data Index: 1592898 (The Pile)

Max Activating Token Index: 571

Text #8

Max Range: 1.9410. Min Range: -1.9410

Max Act: 1.4673. Min Act: -0.0000

Data Index: 1844261 (The Pile)

Max Activating Token Index: 206

Text #9

Max Range: 1.9410. Min Range: -1.9410

Max Act: 1.4757. Min Act: -0.0000

Data Index: 1779646 (The Pile)

Max Activating Token Index: 290

Text #10

Max Range: 1.9410. Min Range: -1.9410

Max Act: 1.2927. Min Act: -0.0000

Data Index: 475209 (The Pile)

Max Activating Token Index: 344

Text #11

Max Range: 1.9410. Min Range: -1.9410

Max Act: 1.4194. Min Act: -0.0000

Data Index: 1554912 (The Pile)

Max Activating Token Index: 791

Text #12

Max Range: 1.9410. Min Range: -1.9410

Max Act: 1.3294. Min Act: -0.0000

Data Index: 1473373 (The Pile)

Max Activating Token Index: 551

Text #13

Max Range: 1.9410. Min Range: -1.9410

Max Act: 1.3350. Min Act: -0.0000

Data Index: 388396 (The Pile)

Max Activating Token Index: 531

Text #14

Max Range: 1.9410. Min Range: -1.9410

Max Act: 1.3298. Min Act: -0.0000

Data Index: 632166 (The Pile)

Max Activating Token Index: 128

Text #15

Max Range: 1.9410. Min Range: -1.9410

Max Act: 1.3019. Min Act: -0.0000

Data Index: 1780374 (The Pile)

Max Activating Token Index: 84

Text #16

Max Range: 1.9410. Min Range: -1.9410

Max Act: 1.3084. Min Act: -0.0000

Data Index: 893309 (The Pile)

Max Activating Token Index: 114

Text #17

Max Range: 1.9410. Min Range: -1.9410

Max Act: 1.2185. Min Act: 0.0000

Data Index: 1815368 (The Pile)

Max Activating Token Index: 76

Text #18

Max Range: 1.9410. Min Range: -1.9410

Max Act: 1.2990. Min Act: -0.0000

Data Index: 1752930 (The Pile)

Max Activating Token Index: 257

Text #19

Max Range: 1.9410. Min Range: -1.9410

Max Act: 1.2928. Min Act: -0.0000

Data Index: 321045 (The Pile)

Max Activating Token Index: 354