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

Dataset: The Pile

Neuron 4445 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1307. Min Range: -3.1307

Max Act: 3.1307. Min Act: -0.0000

Data Index: 495172 (The Pile)

Max Activating Token Index: 844

Text #1

Max Range: 3.1307. Min Range: -3.1307

Max Act: 3.0941. Min Act: -0.0000

Data Index: 332256 (The Pile)

Max Activating Token Index: 680

Text #2

Max Range: 3.1307. Min Range: -3.1307

Max Act: 3.0934. Min Act: -0.0000

Data Index: 1332456 (The Pile)

Max Activating Token Index: 265

Text #3

Max Range: 3.1307. Min Range: -3.1307

Max Act: 3.0150. Min Act: -0.0000

Data Index: 1155367 (The Pile)

Max Activating Token Index: 87

Text #4

Max Range: 3.1307. Min Range: -3.1307

Max Act: 2.7279. Min Act: -0.0000

Data Index: 1782368 (The Pile)

Max Activating Token Index: 547

Text #5

Max Range: 3.1307. Min Range: -3.1307

Max Act: 2.8434. Min Act: -0.0000

Data Index: 1205694 (The Pile)

Max Activating Token Index: 674

Text #6

Max Range: 3.1307. Min Range: -3.1307

Max Act: 2.8390. Min Act: -0.0000

Data Index: 1966400 (The Pile)

Max Activating Token Index: 360

Text #7

Max Range: 3.1307. Min Range: -3.1307

Max Act: 2.9202. Min Act: -0.0000

Data Index: 965275 (The Pile)

Max Activating Token Index: 899

Text #8

Max Range: 3.1307. Min Range: -3.1307

Max Act: 2.7701. Min Act: -0.0000

Data Index: 1633053 (The Pile)

Max Activating Token Index: 580

Text #9

Max Range: 3.1307. Min Range: -3.1307

Max Act: 2.7334. Min Act: -0.0000

Data Index: 753140 (The Pile)

Max Activating Token Index: 167

Text #10

Max Range: 3.1307. Min Range: -3.1307

Max Act: 2.7292. Min Act: -0.0000

Data Index: 1275841 (The Pile)

Max Activating Token Index: 269

Text #11

Max Range: 3.1307. Min Range: -3.1307

Max Act: 2.7025. Min Act: -0.0000

Data Index: 1109139 (The Pile)

Max Activating Token Index: 853

Text #12

Max Range: 3.1307. Min Range: -3.1307

Max Act: 2.5527. Min Act: -0.0000

Data Index: 1021428 (The Pile)

Max Activating Token Index: 850

Text #13

Max Range: 3.1307. Min Range: -3.1307

Max Act: 2.8321. Min Act: -0.0000

Data Index: 629695 (The Pile)

Max Activating Token Index: 223

Text #14

Max Range: 3.1307. Min Range: -3.1307

Max Act: 2.8206. Min Act: -0.0000

Data Index: 1152572 (The Pile)

Max Activating Token Index: 831

Text #15

Max Range: 3.1307. Min Range: -3.1307

Max Act: 2.6901. Min Act: -0.0000

Data Index: 1505351 (The Pile)

Max Activating Token Index: 596

Text #16

Max Range: 3.1307. Min Range: -3.1307

Max Act: 2.6479. Min Act: -0.0000

Data Index: 1014319 (The Pile)

Max Activating Token Index: 1014

Text #17

Max Range: 3.1307. Min Range: -3.1307

Max Act: 2.5006. Min Act: -0.0000

Data Index: 1946535 (The Pile)

Max Activating Token Index: 152

Text #18

Max Range: 3.1307. Min Range: -3.1307

Max Act: 2.6295. Min Act: -0.0000

Data Index: 296851 (The Pile)

Max Activating Token Index: 211

Text #19

Max Range: 3.1307. Min Range: -3.1307

Max Act: 2.4911. Min Act: -0.0000

Data Index: 1620788 (The Pile)

Max Activating Token Index: 476