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

Dataset: The Pile

Neuron 3854 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: 0.7351. Min Range: -0.7351

Max Act: 0.7267. Min Act: -0.0000

Data Index: 412470 (The Pile)

Max Activating Token Index: 647

Text #1

Max Range: 0.7351. Min Range: -0.7351

Max Act: 0.6128. Min Act: -0.0000

Data Index: 1679644 (The Pile)

Max Activating Token Index: 262

Text #2

Max Range: 0.7351. Min Range: -0.7351

Max Act: 0.7351. Min Act: -0.0000

Data Index: 1247647 (The Pile)

Max Activating Token Index: 221

Text #3

Max Range: 0.7351. Min Range: -0.7351

Max Act: 0.5596. Min Act: -0.0000

Data Index: 1907457 (The Pile)

Max Activating Token Index: 630

Text #4

Max Range: 0.7351. Min Range: -0.7351

Max Act: 0.4646. Min Act: -0.0000

Data Index: 88485 (The Pile)

Max Activating Token Index: 889

Text #5

Max Range: 0.7351. Min Range: -0.7351

Max Act: 0.6478. Min Act: -0.0000

Data Index: 1756852 (The Pile)

Max Activating Token Index: 299

Text #6

Max Range: 0.7351. Min Range: -0.7351

Max Act: 0.5130. Min Act: -0.0000

Data Index: 254927 (The Pile)

Max Activating Token Index: 163

Text #7

Max Range: 0.7351. Min Range: -0.7351

Max Act: 0.5598. Min Act: -0.0000

Data Index: 1137513 (The Pile)

Max Activating Token Index: 780

Text #8

Max Range: 0.7351. Min Range: -0.7351

Max Act: 0.5353. Min Act: -0.0000

Data Index: 1287345 (The Pile)

Max Activating Token Index: 136

Text #9

Max Range: 0.7351. Min Range: -0.7351

Max Act: 0.5491. Min Act: -0.0000

Data Index: 980653 (The Pile)

Max Activating Token Index: 116

Text #10

Max Range: 0.7351. Min Range: -0.7351

Max Act: 0.4225. Min Act: -0.0000

Data Index: 186504 (The Pile)

Max Activating Token Index: 728

Text #11

Max Range: 0.7351. Min Range: -0.7351

Max Act: 0.5043. Min Act: -0.0000

Data Index: 1083082 (The Pile)

Max Activating Token Index: 372

Text #12

Max Range: 0.7351. Min Range: -0.7351

Max Act: 0.4956. Min Act: -0.0000

Data Index: 232981 (The Pile)

Max Activating Token Index: 336

Text #13

Max Range: 0.7351. Min Range: -0.7351

Max Act: 0.5248. Min Act: -0.0000

Data Index: 1480845 (The Pile)

Max Activating Token Index: 611

Text #14

Max Range: 0.7351. Min Range: -0.7351

Max Act: 0.4865. Min Act: -0.0000

Data Index: 293478 (The Pile)

Max Activating Token Index: 582

Text #15

Max Range: 0.7351. Min Range: -0.7351

Max Act: 0.4733. Min Act: -0.0000

Data Index: 254967 (The Pile)

Max Activating Token Index: 19

Text #16

Max Range: 0.7351. Min Range: -0.7351

Max Act: 0.4725. Min Act: -0.0000

Data Index: 1072353 (The Pile)

Max Activating Token Index: 626

Text #17

Max Range: 0.7351. Min Range: -0.7351

Max Act: 0.4128. Min Act: -0.0000

Data Index: 1251661 (The Pile)

Max Activating Token Index: 646

Text #18

Max Range: 0.7351. Min Range: -0.7351

Max Act: 0.5231. Min Act: -0.0000

Data Index: 1655095 (The Pile)

Max Activating Token Index: 738

Text #19

Max Range: 0.7351. Min Range: -0.7351

Max Act: 0.4369. Min Act: -0.0000

Data Index: 1376337 (The Pile)

Max Activating Token Index: 563