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

Dataset: The Pile

Neuron 3801 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8113. Min Range: -0.8113

Max Act: 0.8113. Min Act: -0.0000

Data Index: 868446 (The Pile)

Max Activating Token Index: 306

Text #1

Max Range: 0.8113. Min Range: -0.8113

Max Act: 0.6579. Min Act: -0.0000

Data Index: 785869 (The Pile)

Max Activating Token Index: 84

Text #2

Max Range: 0.8113. Min Range: -0.8113

Max Act: 0.6244. Min Act: -0.0000

Data Index: 1161985 (The Pile)

Max Activating Token Index: 488

Text #3

Max Range: 0.8113. Min Range: -0.8113

Max Act: 0.6358. Min Act: -0.0000

Data Index: 589407 (The Pile)

Max Activating Token Index: 735

Text #4

Max Range: 0.8113. Min Range: -0.8113

Max Act: 0.5731. Min Act: -0.0000

Data Index: 1296637 (The Pile)

Max Activating Token Index: 59

Text #5

Max Range: 0.8113. Min Range: -0.8113

Max Act: 0.5743. Min Act: -0.0000

Data Index: 689558 (The Pile)

Max Activating Token Index: 177

Text #6

Max Range: 0.8113. Min Range: -0.8113

Max Act: 0.5724. Min Act: -0.0000

Data Index: 1908641 (The Pile)

Max Activating Token Index: 590

Text #7

Max Range: 0.8113. Min Range: -0.8113

Max Act: 0.5338. Min Act: -0.0000

Data Index: 1768267 (The Pile)

Max Activating Token Index: 85

Text #8

Max Range: 0.8113. Min Range: -0.8113

Max Act: 0.5519. Min Act: -0.0000

Data Index: 1594913 (The Pile)

Max Activating Token Index: 562

Text #9

Max Range: 0.8113. Min Range: -0.8113

Max Act: 0.5800. Min Act: -0.0000

Data Index: 466144 (The Pile)

Max Activating Token Index: 898

Text #10

Max Range: 0.8113. Min Range: -0.8113

Max Act: 0.5273. Min Act: -0.0000

Data Index: 1156085 (The Pile)

Max Activating Token Index: 299

Text #11

Max Range: 0.8113. Min Range: -0.8113

Max Act: 0.5284. Min Act: -0.0000

Data Index: 1536421 (The Pile)

Max Activating Token Index: 275

Text #12

Max Range: 0.8113. Min Range: -0.8113

Max Act: 0.5432. Min Act: -0.0000

Data Index: 988914 (The Pile)

Max Activating Token Index: 419

Text #13

Max Range: 0.8113. Min Range: -0.8113

Max Act: 0.5268. Min Act: -0.0000

Data Index: 1554522 (The Pile)

Max Activating Token Index: 939

Text #14

Max Range: 0.8113. Min Range: -0.8113

Max Act: 0.5009. Min Act: -0.0000

Data Index: 634669 (The Pile)

Max Activating Token Index: 114

Text #15

Max Range: 0.8113. Min Range: -0.8113

Max Act: 0.5175. Min Act: -0.0000

Data Index: 1364274 (The Pile)

Max Activating Token Index: 357

Text #16

Max Range: 0.8113. Min Range: -0.8113

Max Act: 0.5025. Min Act: -0.0000

Data Index: 1883898 (The Pile)

Max Activating Token Index: 150

Text #17

Max Range: 0.8113. Min Range: -0.8113

Max Act: 0.4983. Min Act: -0.0000

Data Index: 710642 (The Pile)

Max Activating Token Index: 634

Text #18

Max Range: 0.8113. Min Range: -0.8113

Max Act: 0.4965. Min Act: -0.0000

Data Index: 1957077 (The Pile)

Max Activating Token Index: 327

Text #19

Max Range: 0.8113. Min Range: -0.8113

Max Act: 0.5272. Min Act: -0.0000

Data Index: 1248930 (The Pile)

Max Activating Token Index: 459