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

Dataset: The Pile

Neuron 3639 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: 1.8562. Min Range: -1.8562

Max Act: 1.8562. Min Act: -0.0000

Data Index: 466593 (The Pile)

Max Activating Token Index: 471

Text #1

Max Range: 1.8562. Min Range: -1.8562

Max Act: 1.5893. Min Act: -0.0000

Data Index: 1551059 (The Pile)

Max Activating Token Index: 604

Text #2

Max Range: 1.8562. Min Range: -1.8562

Max Act: 1.2841. Min Act: -0.0000

Data Index: 1646477 (The Pile)

Max Activating Token Index: 363

Text #3

Max Range: 1.8562. Min Range: -1.8562

Max Act: 1.3729. Min Act: -0.0000

Data Index: 6324 (The Pile)

Max Activating Token Index: 607

Text #4

Max Range: 1.8562. Min Range: -1.8562

Max Act: 1.2120. Min Act: -0.0000

Data Index: 617141 (The Pile)

Max Activating Token Index: 91

Text #5

Max Range: 1.8562. Min Range: -1.8562

Max Act: 1.3195. Min Act: -0.0000

Data Index: 1596976 (The Pile)

Max Activating Token Index: 281

Text #6

Max Range: 1.8562. Min Range: -1.8562

Max Act: 1.2218. Min Act: -0.0000

Data Index: 1739243 (The Pile)

Max Activating Token Index: 413

Text #7

Max Range: 1.8562. Min Range: -1.8562

Max Act: 1.2927. Min Act: -0.0000

Data Index: 1729005 (The Pile)

Max Activating Token Index: 292

Text #8

Max Range: 1.8562. Min Range: -1.8562

Max Act: 1.2183. Min Act: -0.0000

Data Index: 919707 (The Pile)

Max Activating Token Index: 394

Text #9

Max Range: 1.8562. Min Range: -1.8562

Max Act: 1.1994. Min Act: -0.0000

Data Index: 857044 (The Pile)

Max Activating Token Index: 980

Text #10

Max Range: 1.8562. Min Range: -1.8562

Max Act: 1.2018. Min Act: -0.0000

Data Index: 1366741 (The Pile)

Max Activating Token Index: 336

Text #11

Max Range: 1.8562. Min Range: -1.8562

Max Act: 1.1619. Min Act: -0.0000

Data Index: 1281806 (The Pile)

Max Activating Token Index: 882

Text #12

Max Range: 1.8562. Min Range: -1.8562

Max Act: 1.1462. Min Act: -0.0000

Data Index: 1708141 (The Pile)

Max Activating Token Index: 232

Text #13

Max Range: 1.8562. Min Range: -1.8562

Max Act: 1.1099. Min Act: -0.0000

Data Index: 1558332 (The Pile)

Max Activating Token Index: 351

Text #14

Max Range: 1.8562. Min Range: -1.8562

Max Act: 1.2102. Min Act: -0.0000

Data Index: 1003121 (The Pile)

Max Activating Token Index: 733

Text #15

Max Range: 1.8562. Min Range: -1.8562

Max Act: 1.1714. Min Act: -0.0000

Data Index: 1023538 (The Pile)

Max Activating Token Index: 245

Text #16

Max Range: 1.8562. Min Range: -1.8562

Max Act: 1.0867. Min Act: -0.0000

Data Index: 756272 (The Pile)

Max Activating Token Index: 123

Text #17

Max Range: 1.8562. Min Range: -1.8562

Max Act: 1.0892. Min Act: -0.0000

Data Index: 687911 (The Pile)

Max Activating Token Index: 492

Text #18

Max Range: 1.8562. Min Range: -1.8562

Max Act: 1.1152. Min Act: -0.0000

Data Index: 1474820 (The Pile)

Max Activating Token Index: 909

Text #19

Max Range: 1.8562. Min Range: -1.8562

Max Act: 1.1116. Min Act: -0.0000

Data Index: 1170204 (The Pile)

Max Activating Token Index: 512