Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1891 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.1536. Min Act: -0.0000

Data Index: 1498390 (The Pile)

Max Activating Token Index: 61

Text #1

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.1493. Min Act: -0.0000

Data Index: 286833 (The Pile)

Max Activating Token Index: 409

Text #2

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.1296. Min Act: -0.0000

Data Index: 73126 (The Pile)

Max Activating Token Index: 695

Text #3

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.1275. Min Act: -0.0000

Data Index: 1741956 (The Pile)

Max Activating Token Index: 816

Text #4

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.1280. Min Act: -0.0000

Data Index: 497439 (The Pile)

Max Activating Token Index: 368

Text #5

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.1094. Min Act: -0.0000

Data Index: 728743 (The Pile)

Max Activating Token Index: 377

Text #6

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.1238. Min Act: -0.0000

Data Index: 1764269 (The Pile)

Max Activating Token Index: 182

Text #7

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.1249. Min Act: -0.0000

Data Index: 1310580 (The Pile)

Max Activating Token Index: 442

Text #8

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.1298. Min Act: -0.0000

Data Index: 250036 (The Pile)

Max Activating Token Index: 814

Text #9

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.1116. Min Act: -0.0000

Data Index: 1204844 (The Pile)

Max Activating Token Index: 670

Text #10

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.1243. Min Act: -0.0000

Data Index: 1197440 (The Pile)

Max Activating Token Index: 1017

Text #11

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.1237. Min Act: -0.0000

Data Index: 1034010 (The Pile)

Max Activating Token Index: 32

Text #12

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.1234. Min Act: -0.0000

Data Index: 83154 (The Pile)

Max Activating Token Index: 376

Text #13

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.1307. Min Act: -0.0000

Data Index: 1218695 (The Pile)

Max Activating Token Index: 986

Text #14

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.1131. Min Act: -0.0000

Data Index: 1015052 (The Pile)

Max Activating Token Index: 840

Text #15

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.1180. Min Act: -0.0000

Data Index: 868995 (The Pile)

Max Activating Token Index: 366

Text #16

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.1271. Min Act: -0.0000

Data Index: 1103048 (The Pile)

Max Activating Token Index: 628

Text #17

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.1187. Min Act: -0.0000

Data Index: 1502149 (The Pile)

Max Activating Token Index: 417

Text #18

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.1184. Min Act: -0.0000

Data Index: 1907815 (The Pile)

Max Activating Token Index: 111

Text #19

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.1266. Min Act: -0.0000

Data Index: 1963556 (The Pile)

Max Activating Token Index: 166