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

Dataset: The Pile

Neuron 3340 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2726. Min Range: -0.2726

Max Act: 0.2694. Min Act: -0.0000

Data Index: 1840004 (The Pile)

Max Activating Token Index: 464

Text #1

Max Range: 0.2726. Min Range: -0.2726

Max Act: 0.2726. Min Act: -0.0000

Data Index: 1180176 (The Pile)

Max Activating Token Index: 993

Text #2

Max Range: 0.2726. Min Range: -0.2726

Max Act: 0.2559. Min Act: -0.0000

Data Index: 1668176 (The Pile)

Max Activating Token Index: 739

Text #3

Max Range: 0.2726. Min Range: -0.2726

Max Act: 0.2357. Min Act: -0.0000

Data Index: 1780006 (The Pile)

Max Activating Token Index: 98

Text #4

Max Range: 0.2726. Min Range: -0.2726

Max Act: 0.2252. Min Act: -0.0000

Data Index: 1761793 (The Pile)

Max Activating Token Index: 216

Text #5

Max Range: 0.2726. Min Range: -0.2726

Max Act: 0.2228. Min Act: -0.0000

Data Index: 1721882 (The Pile)

Max Activating Token Index: 98

Text #6

Max Range: 0.2726. Min Range: -0.2726

Max Act: 0.2217. Min Act: -0.0000

Data Index: 1442121 (The Pile)

Max Activating Token Index: 729

Text #7

Max Range: 0.2726. Min Range: -0.2726

Max Act: 0.2134. Min Act: -0.0000

Data Index: 87354 (The Pile)

Max Activating Token Index: 79

Text #8

Max Range: 0.2726. Min Range: -0.2726

Max Act: 0.2203. Min Act: -0.0000

Data Index: 341423 (The Pile)

Max Activating Token Index: 179

Text #9

Max Range: 0.2726. Min Range: -0.2726

Max Act: 0.2193. Min Act: -0.0000

Data Index: 1959250 (The Pile)

Max Activating Token Index: 831

Text #10

Max Range: 0.2726. Min Range: -0.2726

Max Act: 0.2188. Min Act: -0.0000

Data Index: 1296348 (The Pile)

Max Activating Token Index: 669

Text #11

Max Range: 0.2726. Min Range: -0.2726

Max Act: 0.2331. Min Act: -0.0000

Data Index: 897166 (The Pile)

Max Activating Token Index: 964

Text #12

Max Range: 0.2726. Min Range: -0.2726

Max Act: 0.2088. Min Act: -0.0000

Data Index: 427261 (The Pile)

Max Activating Token Index: 261

Text #13

Max Range: 0.2726. Min Range: -0.2726

Max Act: 0.2162. Min Act: -0.0000

Data Index: 554714 (The Pile)

Max Activating Token Index: 265

Text #14

Max Range: 0.2726. Min Range: -0.2726

Max Act: 0.2012. Min Act: -0.0000

Data Index: 1119297 (The Pile)

Max Activating Token Index: 626

Text #15

Max Range: 0.2726. Min Range: -0.2726

Max Act: 0.2031. Min Act: -0.0000

Data Index: 645953 (The Pile)

Max Activating Token Index: 582

Text #16

Max Range: 0.2726. Min Range: -0.2726

Max Act: 0.2074. Min Act: -0.0000

Data Index: 534549 (The Pile)

Max Activating Token Index: 238

Text #17

Max Range: 0.2726. Min Range: -0.2726

Max Act: 0.2119. Min Act: -0.0000

Data Index: 1245319 (The Pile)

Max Activating Token Index: 215

Text #18

Max Range: 0.2726. Min Range: -0.2726

Max Act: 0.2126. Min Act: -0.0000

Data Index: 1418664 (The Pile)

Max Activating Token Index: 531

Text #19

Max Range: 0.2726. Min Range: -0.2726

Max Act: 0.2075. Min Act: -0.0000

Data Index: 1462120 (The Pile)

Max Activating Token Index: 473