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

Dataset: The Pile

Neuron 1005 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: 0.7265. Min Range: -0.7265

Max Act: 0.6281. Min Act: -0.0000

Data Index: 969625 (The Pile)

Max Activating Token Index: 1014

Text #1

Max Range: 0.7265. Min Range: -0.7265

Max Act: 0.6757. Min Act: -0.0000

Data Index: 1738318 (The Pile)

Max Activating Token Index: 344

Text #2

Max Range: 0.7265. Min Range: -0.7265

Max Act: 0.6904. Min Act: -0.0000

Data Index: 1900068 (The Pile)

Max Activating Token Index: 510

Text #3

Max Range: 0.7265. Min Range: -0.7265

Max Act: 0.6543. Min Act: -0.0000

Data Index: 300765 (The Pile)

Max Activating Token Index: 338

Text #4

Max Range: 0.7265. Min Range: -0.7265

Max Act: 0.6472. Min Act: -0.0000

Data Index: 430986 (The Pile)

Max Activating Token Index: 346

Text #5

Max Range: 0.7265. Min Range: -0.7265

Max Act: 0.5124. Min Act: -0.0000

Data Index: 1216647 (The Pile)

Max Activating Token Index: 720

Text #6

Max Range: 0.7265. Min Range: -0.7265

Max Act: 0.6998. Min Act: -0.0000

Data Index: 1128989 (The Pile)

Max Activating Token Index: 154

Text #7

Max Range: 0.7265. Min Range: -0.7265

Max Act: 0.5915. Min Act: -0.0000

Data Index: 846488 (The Pile)

Max Activating Token Index: 300

Text #8

Max Range: 0.7265. Min Range: -0.7265

Max Act: 0.6132. Min Act: -0.0000

Data Index: 1637542 (The Pile)

Max Activating Token Index: 217

Text #9

Max Range: 0.7265. Min Range: -0.7265

Max Act: 0.5912. Min Act: -0.0000

Data Index: 1808974 (The Pile)

Max Activating Token Index: 353

Text #10

Max Range: 0.7265. Min Range: -0.7265

Max Act: 0.5984. Min Act: -0.0000

Data Index: 1643976 (The Pile)

Max Activating Token Index: 866

Text #11

Max Range: 0.7265. Min Range: -0.7265

Max Act: 0.6372. Min Act: -0.0000

Data Index: 583731 (The Pile)

Max Activating Token Index: 935

Text #12

Max Range: 0.7265. Min Range: -0.7265

Max Act: 0.5689. Min Act: -0.0000

Data Index: 1799190 (The Pile)

Max Activating Token Index: 337

Text #13

Max Range: 0.7265. Min Range: -0.7265

Max Act: 0.5909. Min Act: -0.0000

Data Index: 510774 (The Pile)

Max Activating Token Index: 621

Text #14

Max Range: 0.7265. Min Range: -0.7265

Max Act: 0.6121. Min Act: -0.0000

Data Index: 1799813 (The Pile)

Max Activating Token Index: 374

Text #15

Max Range: 0.7265. Min Range: -0.7265

Max Act: 0.7265. Min Act: -0.0000

Data Index: 1622436 (The Pile)

Max Activating Token Index: 781

Text #16

Max Range: 0.7265. Min Range: -0.7265

Max Act: 0.5629. Min Act: -0.0000

Data Index: 845532 (The Pile)

Max Activating Token Index: 962

Text #17

Max Range: 0.7265. Min Range: -0.7265

Max Act: 0.5141. Min Act: -0.0000

Data Index: 344959 (The Pile)

Max Activating Token Index: 189

Text #18

Max Range: 0.7265. Min Range: -0.7265

Max Act: 0.6151. Min Act: -0.0000

Data Index: 456223 (The Pile)

Max Activating Token Index: 586

Text #19

Max Range: 0.7265. Min Range: -0.7265

Max Act: 0.4904. Min Act: -0.0000

Data Index: 1110731 (The Pile)

Max Activating Token Index: 220