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

Dataset: The Pile

Neuron 266 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: 1.9482. Min Range: -1.9482

Max Act: 1.6709. Min Act: -0.0000

Data Index: 1594727 (The Pile)

Max Activating Token Index: 770

Text #1

Max Range: 1.9482. Min Range: -1.9482

Max Act: 1.9482. Min Act: -0.0000

Data Index: 1439334 (The Pile)

Max Activating Token Index: 342

Text #2

Max Range: 1.9482. Min Range: -1.9482

Max Act: 1.7065. Min Act: -0.0000

Data Index: 929434 (The Pile)

Max Activating Token Index: 1022

Text #3

Max Range: 1.9482. Min Range: -1.9482

Max Act: 1.8660. Min Act: -0.0000

Data Index: 1791247 (The Pile)

Max Activating Token Index: 844

Text #4

Max Range: 1.9482. Min Range: -1.9482

Max Act: 1.7140. Min Act: -0.0000

Data Index: 1908341 (The Pile)

Max Activating Token Index: 306

Text #5

Max Range: 1.9482. Min Range: -1.9482

Max Act: 1.5379. Min Act: -0.0000

Data Index: 1896459 (The Pile)

Max Activating Token Index: 176

Text #6

Max Range: 1.9482. Min Range: -1.9482

Max Act: 1.6124. Min Act: -0.0000

Data Index: 1206012 (The Pile)

Max Activating Token Index: 649

Text #7

Max Range: 1.9482. Min Range: -1.9482

Max Act: 1.5605. Min Act: -0.0000

Data Index: 1544789 (The Pile)

Max Activating Token Index: 636

Text #8

Max Range: 1.9482. Min Range: -1.9482

Max Act: 1.4165. Min Act: -0.0000

Data Index: 228092 (The Pile)

Max Activating Token Index: 305

Text #9

Max Range: 1.9482. Min Range: -1.9482

Max Act: 1.5227. Min Act: -0.0000

Data Index: 579486 (The Pile)

Max Activating Token Index: 769

Text #10

Max Range: 1.9482. Min Range: -1.9482

Max Act: 1.5262. Min Act: -0.0000

Data Index: 1193975 (The Pile)

Max Activating Token Index: 944

Text #11

Max Range: 1.9482. Min Range: -1.9482

Max Act: 1.4326. Min Act: -0.0000

Data Index: 309836 (The Pile)

Max Activating Token Index: 777

Text #12

Max Range: 1.9482. Min Range: -1.9482

Max Act: 1.5959. Min Act: -0.0000

Data Index: 1608428 (The Pile)

Max Activating Token Index: 774

Text #13

Max Range: 1.9482. Min Range: -1.9482

Max Act: 1.5367. Min Act: -0.0000

Data Index: 543433 (The Pile)

Max Activating Token Index: 770

Text #14

Max Range: 1.9482. Min Range: -1.9482

Max Act: 1.4124. Min Act: -0.0000

Data Index: 366832 (The Pile)

Max Activating Token Index: 508

Text #15

Max Range: 1.9482. Min Range: -1.9482

Max Act: 1.4187. Min Act: -0.0000

Data Index: 1205135 (The Pile)

Max Activating Token Index: 38

Text #16

Max Range: 1.9482. Min Range: -1.9482

Max Act: 1.4745. Min Act: -0.0000

Data Index: 327427 (The Pile)

Max Activating Token Index: 966

Text #17

Max Range: 1.9482. Min Range: -1.9482

Max Act: 1.5531. Min Act: -0.0000

Data Index: 476915 (The Pile)

Max Activating Token Index: 487

Text #18

Max Range: 1.9482. Min Range: -1.9482

Max Act: 1.4235. Min Act: -0.0000

Data Index: 467901 (The Pile)

Max Activating Token Index: 141

Text #19

Max Range: 1.9482. Min Range: -1.9482

Max Act: 1.4826. Min Act: -0.0000

Data Index: 1720670 (The Pile)

Max Activating Token Index: 669