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

Dataset: The Pile

Neuron 4445 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2846. Min Range: -0.2846

Max Act: 0.2846. Min Act: -0.0000

Data Index: 437797 (The Pile)

Max Activating Token Index: 889

Text #1

Max Range: 0.2846. Min Range: -0.2846

Max Act: 0.2236. Min Act: -0.0000

Data Index: 1968115 (The Pile)

Max Activating Token Index: 547

Text #2

Max Range: 0.2846. Min Range: -0.2846

Max Act: 0.2360. Min Act: -0.0000

Data Index: 1738005 (The Pile)

Max Activating Token Index: 114

Text #3

Max Range: 0.2846. Min Range: -0.2846

Max Act: 0.2199. Min Act: -0.0000

Data Index: 214835 (The Pile)

Max Activating Token Index: 370

Text #4

Max Range: 0.2846. Min Range: -0.2846

Max Act: 0.2224. Min Act: -0.0000

Data Index: 1842472 (The Pile)

Max Activating Token Index: 129

Text #5

Max Range: 0.2846. Min Range: -0.2846

Max Act: 0.2199. Min Act: -0.0000

Data Index: 1967484 (The Pile)

Max Activating Token Index: 158

Text #6

Max Range: 0.2846. Min Range: -0.2846

Max Act: 0.1955. Min Act: -0.0000

Data Index: 91933 (The Pile)

Max Activating Token Index: 771

Text #7

Max Range: 0.2846. Min Range: -0.2846

Max Act: 0.2094. Min Act: -0.0000

Data Index: 1214583 (The Pile)

Max Activating Token Index: 299

Text #8

Max Range: 0.2846. Min Range: -0.2846

Max Act: 0.1914. Min Act: -0.0000

Data Index: 210542 (The Pile)

Max Activating Token Index: 677

Text #9

Max Range: 0.2846. Min Range: -0.2846

Max Act: 0.2172. Min Act: -0.0000

Data Index: 1808792 (The Pile)

Max Activating Token Index: 219

Text #10

Max Range: 0.2846. Min Range: -0.2846

Max Act: 0.2096. Min Act: -0.0000

Data Index: 1425528 (The Pile)

Max Activating Token Index: 45

Text #11

Max Range: 0.2846. Min Range: -0.2846

Max Act: 0.2089. Min Act: -0.0000

Data Index: 933032 (The Pile)

Max Activating Token Index: 176

Text #12

Max Range: 0.2846. Min Range: -0.2846

Max Act: 0.1945. Min Act: -0.0000

Data Index: 954622 (The Pile)

Max Activating Token Index: 321

Text #13

Max Range: 0.2846. Min Range: -0.2846

Max Act: 0.1864. Min Act: -0.0000

Data Index: 646715 (The Pile)

Max Activating Token Index: 252

Text #14

Max Range: 0.2846. Min Range: -0.2846

Max Act: 0.1935. Min Act: -0.0000

Data Index: 1917898 (The Pile)

Max Activating Token Index: 522

Text #15

Max Range: 0.2846. Min Range: -0.2846

Max Act: 0.1971. Min Act: -0.0000

Data Index: 479783 (The Pile)

Max Activating Token Index: 127

Text #16

Max Range: 0.2846. Min Range: -0.2846

Max Act: 0.1792. Min Act: -0.0000

Data Index: 633362 (The Pile)

Max Activating Token Index: 770

Text #17

Max Range: 0.2846. Min Range: -0.2846

Max Act: 0.2035. Min Act: -0.0000

Data Index: 239587 (The Pile)

Max Activating Token Index: 269

Text #18

Max Range: 0.2846. Min Range: -0.2846

Max Act: 0.2043. Min Act: -0.0000

Data Index: 118166 (The Pile)

Max Activating Token Index: 37

Text #19

Max Range: 0.2846. Min Range: -0.2846

Max Act: 0.1775. Min Act: -0.0000

Data Index: 4824 (The Pile)

Max Activating Token Index: 317