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

Dataset: The Pile

Neuron 2222 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: 0.1789. Min Range: -0.1789

Max Act: 0.1789. Min Act: -0.0000

Data Index: 1336324 (The Pile)

Max Activating Token Index: 719

Text #1

Max Range: 0.1789. Min Range: -0.1789

Max Act: 0.1657. Min Act: -0.0000

Data Index: 1639192 (The Pile)

Max Activating Token Index: 825

Text #2

Max Range: 0.1789. Min Range: -0.1789

Max Act: 0.1559. Min Act: -0.0000

Data Index: 621275 (The Pile)

Max Activating Token Index: 138

Text #3

Max Range: 0.1789. Min Range: -0.1789

Max Act: 0.1405. Min Act: -0.0000

Data Index: 465298 (The Pile)

Max Activating Token Index: 532

Text #4

Max Range: 0.1789. Min Range: -0.1789

Max Act: 0.1367. Min Act: -0.0000

Data Index: 708565 (The Pile)

Max Activating Token Index: 179

Text #5

Max Range: 0.1789. Min Range: -0.1789

Max Act: 0.1432. Min Act: -0.0000

Data Index: 1949630 (The Pile)

Max Activating Token Index: 276

Text #6

Max Range: 0.1789. Min Range: -0.1789

Max Act: 0.1349. Min Act: -0.0000

Data Index: 791143 (The Pile)

Max Activating Token Index: 544

Text #7

Max Range: 0.1789. Min Range: -0.1789

Max Act: 0.1240. Min Act: -0.0000

Data Index: 1895108 (The Pile)

Max Activating Token Index: 774

Text #8

Max Range: 0.1789. Min Range: -0.1789

Max Act: 0.1263. Min Act: -0.0000

Data Index: 933075 (The Pile)

Max Activating Token Index: 160

Text #9

Max Range: 0.1789. Min Range: -0.1789

Max Act: 0.1302. Min Act: -0.0000

Data Index: 1434117 (The Pile)

Max Activating Token Index: 464

Text #10

Max Range: 0.1789. Min Range: -0.1789

Max Act: 0.1224. Min Act: -0.0000

Data Index: 1447935 (The Pile)

Max Activating Token Index: 319

Text #11

Max Range: 0.1789. Min Range: -0.1789

Max Act: 0.1184. Min Act: -0.0000

Data Index: 1317549 (The Pile)

Max Activating Token Index: 602

Text #12

Max Range: 0.1789. Min Range: -0.1789

Max Act: 0.1204. Min Act: -0.0000

Data Index: 365483 (The Pile)

Max Activating Token Index: 593

Text #13

Max Range: 0.1789. Min Range: -0.1789

Max Act: 0.1190. Min Act: -0.0000

Data Index: 318065 (The Pile)

Max Activating Token Index: 492

Text #14

Max Range: 0.1789. Min Range: -0.1789

Max Act: 0.1064. Min Act: -0.0000

Data Index: 1625079 (The Pile)

Max Activating Token Index: 862

Text #15

Max Range: 0.1789. Min Range: -0.1789

Max Act: 0.1186. Min Act: -0.0000

Data Index: 879975 (The Pile)

Max Activating Token Index: 24

Text #16

Max Range: 0.1789. Min Range: -0.1789

Max Act: 0.1202. Min Act: -0.0000

Data Index: 903270 (The Pile)

Max Activating Token Index: 914

Text #17

Max Range: 0.1789. Min Range: -0.1789

Max Act: 0.1139. Min Act: -0.0000

Data Index: 1725622 (The Pile)

Max Activating Token Index: 1002

Text #18

Max Range: 0.1789. Min Range: -0.1789

Max Act: 0.1092. Min Act: -0.0000

Data Index: 1160911 (The Pile)

Max Activating Token Index: 393

Text #19

Max Range: 0.1789. Min Range: -0.1789

Max Act: 0.1163. Min Act: -0.0000

Data Index: 644771 (The Pile)

Max Activating Token Index: 142