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

Dataset: The Pile

Neuron 2139 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3059. Min Range: -0.3059

Max Act: 0.3059. Min Act: -0.0000

Data Index: 1498333 (The Pile)

Max Activating Token Index: 411

Text #1

Max Range: 0.3059. Min Range: -0.3059

Max Act: 0.3027. Min Act: -0.0000

Data Index: 240231 (The Pile)

Max Activating Token Index: 935

Text #2

Max Range: 0.3059. Min Range: -0.3059

Max Act: 0.2555. Min Act: -0.0000

Data Index: 1863072 (The Pile)

Max Activating Token Index: 180

Text #3

Max Range: 0.3059. Min Range: -0.3059

Max Act: 0.2270. Min Act: -0.0000

Data Index: 1546372 (The Pile)

Max Activating Token Index: 679

Text #4

Max Range: 0.3059. Min Range: -0.3059

Max Act: 0.2165. Min Act: -0.0000

Data Index: 1286627 (The Pile)

Max Activating Token Index: 278

Text #5

Max Range: 0.3059. Min Range: -0.3059

Max Act: 0.2187. Min Act: -0.0000

Data Index: 1441953 (The Pile)

Max Activating Token Index: 208

Text #6

Max Range: 0.3059. Min Range: -0.3059

Max Act: 0.2141. Min Act: -0.0000

Data Index: 586173 (The Pile)

Max Activating Token Index: 216

Text #7

Max Range: 0.3059. Min Range: -0.3059

Max Act: 0.2246. Min Act: -0.0000

Data Index: 648307 (The Pile)

Max Activating Token Index: 262

Text #8

Max Range: 0.3059. Min Range: -0.3059

Max Act: 0.1980. Min Act: -0.0000

Data Index: 1964600 (The Pile)

Max Activating Token Index: 809

Text #9

Max Range: 0.3059. Min Range: -0.3059

Max Act: 0.2232. Min Act: -0.0000

Data Index: 1568226 (The Pile)

Max Activating Token Index: 617

Text #10

Max Range: 0.3059. Min Range: -0.3059

Max Act: 0.1754. Min Act: -0.0000

Data Index: 1506553 (The Pile)

Max Activating Token Index: 853

Text #11

Max Range: 0.3059. Min Range: -0.3059

Max Act: 0.1856. Min Act: -0.0000

Data Index: 1225014 (The Pile)

Max Activating Token Index: 680

Text #12

Max Range: 0.3059. Min Range: -0.3059

Max Act: 0.2125. Min Act: -0.0000

Data Index: 1932478 (The Pile)

Max Activating Token Index: 106

Text #13

Max Range: 0.3059. Min Range: -0.3059

Max Act: 0.1924. Min Act: -0.0000

Data Index: 1345236 (The Pile)

Max Activating Token Index: 363

Text #14

Max Range: 0.3059. Min Range: -0.3059

Max Act: 0.1972. Min Act: -0.0000

Data Index: 1405011 (The Pile)

Max Activating Token Index: 663

Text #15

Max Range: 0.3059. Min Range: -0.3059

Max Act: 0.1735. Min Act: -0.0000

Data Index: 687072 (The Pile)

Max Activating Token Index: 410

Text #16

Max Range: 0.3059. Min Range: -0.3059

Max Act: 0.1776. Min Act: -0.0000

Data Index: 631775 (The Pile)

Max Activating Token Index: 556

Text #17

Max Range: 0.3059. Min Range: -0.3059

Max Act: 0.1815. Min Act: -0.0000

Data Index: 730081 (The Pile)

Max Activating Token Index: 400

Text #18

Max Range: 0.3059. Min Range: -0.3059

Max Act: 0.1806. Min Act: -0.0000

Data Index: 1630365 (The Pile)

Max Activating Token Index: 632

Text #19

Max Range: 0.3059. Min Range: -0.3059

Max Act: 0.1755. Min Act: -0.0000

Data Index: 129698 (The Pile)

Max Activating Token Index: 296