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

Dataset: The Pile

Neuron 3333 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2353. Min Range: -0.2353

Max Act: 0.2353. Min Act: -0.0000

Data Index: 1527827 (The Pile)

Max Activating Token Index: 541

Text #1

Max Range: 0.2353. Min Range: -0.2353

Max Act: 0.1550. Min Act: -0.0000

Data Index: 1943406 (The Pile)

Max Activating Token Index: 513

Text #2

Max Range: 0.2353. Min Range: -0.2353

Max Act: 0.1494. Min Act: -0.0000

Data Index: 1125619 (The Pile)

Max Activating Token Index: 997

Text #3

Max Range: 0.2353. Min Range: -0.2353

Max Act: 0.1374. Min Act: -0.0000

Data Index: 1623114 (The Pile)

Max Activating Token Index: 390

Text #4

Max Range: 0.2353. Min Range: -0.2353

Max Act: 0.1392. Min Act: -0.0000

Data Index: 1008799 (The Pile)

Max Activating Token Index: 366

Text #5

Max Range: 0.2353. Min Range: -0.2353

Max Act: 0.1363. Min Act: -0.0000

Data Index: 1581412 (The Pile)

Max Activating Token Index: 247

Text #6

Max Range: 0.2353. Min Range: -0.2353

Max Act: 0.1410. Min Act: -0.0000

Data Index: 1336257 (The Pile)

Max Activating Token Index: 555

Text #7

Max Range: 0.2353. Min Range: -0.2353

Max Act: 0.1185. Min Act: -0.0000

Data Index: 237583 (The Pile)

Max Activating Token Index: 182

Text #8

Max Range: 0.2353. Min Range: -0.2353

Max Act: 0.1265. Min Act: -0.0000

Data Index: 1739688 (The Pile)

Max Activating Token Index: 647

Text #9

Max Range: 0.2353. Min Range: -0.2353

Max Act: 0.1276. Min Act: -0.0000

Data Index: 1263725 (The Pile)

Max Activating Token Index: 603

Text #10

Max Range: 0.2353. Min Range: -0.2353

Max Act: 0.1380. Min Act: -0.0000

Data Index: 32019 (The Pile)

Max Activating Token Index: 147

Text #11

Max Range: 0.2353. Min Range: -0.2353

Max Act: 0.1094. Min Act: -0.0000

Data Index: 1802421 (The Pile)

Max Activating Token Index: 696

Text #12

Max Range: 0.2353. Min Range: -0.2353

Max Act: 0.1231. Min Act: -0.0000

Data Index: 1375568 (The Pile)

Max Activating Token Index: 417

Text #13

Max Range: 0.2353. Min Range: -0.2353

Max Act: 0.1183. Min Act: -0.0000

Data Index: 606537 (The Pile)

Max Activating Token Index: 400

Text #14

Max Range: 0.2353. Min Range: -0.2353

Max Act: 0.1224. Min Act: -0.0000

Data Index: 806876 (The Pile)

Max Activating Token Index: 985

Text #15

Max Range: 0.2353. Min Range: -0.2353

Max Act: 0.1222. Min Act: -0.0000

Data Index: 1081834 (The Pile)

Max Activating Token Index: 900

Text #16

Max Range: 0.2353. Min Range: -0.2353

Max Act: 0.1268. Min Act: -0.0000

Data Index: 219665 (The Pile)

Max Activating Token Index: 232

Text #17

Max Range: 0.2353. Min Range: -0.2353

Max Act: 0.1077. Min Act: -0.0000

Data Index: 1150616 (The Pile)

Max Activating Token Index: 469

Text #18

Max Range: 0.2353. Min Range: -0.2353

Max Act: 0.1232. Min Act: -0.0000

Data Index: 789635 (The Pile)

Max Activating Token Index: 108

Text #19

Max Range: 0.2353. Min Range: -0.2353

Max Act: 0.1100. Min Act: -0.0000

Data Index: 291196 (The Pile)

Max Activating Token Index: 986