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

Dataset: The Pile

Neuron 5053 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: 0.8530. Min Range: -0.8530

Max Act: 0.8530. Min Act: -0.0000

Data Index: 111266 (The Pile)

Max Activating Token Index: 356

Text #1

Max Range: 0.8530. Min Range: -0.8530

Max Act: 0.8292. Min Act: -0.0000

Data Index: 127687 (The Pile)

Max Activating Token Index: 376

Text #2

Max Range: 0.8530. Min Range: -0.8530

Max Act: 0.7356. Min Act: -0.0000

Data Index: 420177 (The Pile)

Max Activating Token Index: 172

Text #3

Max Range: 0.8530. Min Range: -0.8530

Max Act: 0.7202. Min Act: -0.0000

Data Index: 1811131 (The Pile)

Max Activating Token Index: 398

Text #4

Max Range: 0.8530. Min Range: -0.8530

Max Act: 0.7141. Min Act: -0.0000

Data Index: 706920 (The Pile)

Max Activating Token Index: 517

Text #5

Max Range: 0.8530. Min Range: -0.8530

Max Act: 0.7045. Min Act: -0.0000

Data Index: 621871 (The Pile)

Max Activating Token Index: 890

Text #6

Max Range: 0.8530. Min Range: -0.8530

Max Act: 0.7123. Min Act: -0.0000

Data Index: 880750 (The Pile)

Max Activating Token Index: 429

Text #7

Max Range: 0.8530. Min Range: -0.8530

Max Act: 0.6527. Min Act: -0.0000

Data Index: 499154 (The Pile)

Max Activating Token Index: 206

Text #8

Max Range: 0.8530. Min Range: -0.8530

Max Act: 0.7077. Min Act: -0.0000

Data Index: 1589714 (The Pile)

Max Activating Token Index: 32

Text #9

Max Range: 0.8530. Min Range: -0.8530

Max Act: 0.6436. Min Act: -0.0000

Data Index: 380897 (The Pile)

Max Activating Token Index: 107

Text #10

Max Range: 0.8530. Min Range: -0.8530

Max Act: 0.7137. Min Act: -0.0000

Data Index: 870804 (The Pile)

Max Activating Token Index: 908

Text #11

Max Range: 0.8530. Min Range: -0.8530

Max Act: 0.6408. Min Act: -0.0000

Data Index: 1712521 (The Pile)

Max Activating Token Index: 457

Text #12

Max Range: 0.8530. Min Range: -0.8530

Max Act: 0.6592. Min Act: -0.0000

Data Index: 1162963 (The Pile)

Max Activating Token Index: 18

Text #13

Max Range: 0.8530. Min Range: -0.8530

Max Act: 0.6010. Min Act: -0.0000

Data Index: 775447 (The Pile)

Max Activating Token Index: 407

Text #14

Max Range: 0.8530. Min Range: -0.8530

Max Act: 0.6395. Min Act: -0.0000

Data Index: 1389050 (The Pile)

Max Activating Token Index: 605

Text #15

Max Range: 0.8530. Min Range: -0.8530

Max Act: 0.6291. Min Act: -0.0000

Data Index: 516408 (The Pile)

Max Activating Token Index: 87

Text #16

Max Range: 0.8530. Min Range: -0.8530

Max Act: 0.6256. Min Act: -0.0000

Data Index: 1401393 (The Pile)

Max Activating Token Index: 248

Text #17

Max Range: 0.8530. Min Range: -0.8530

Max Act: 0.6021. Min Act: -0.0000

Data Index: 1708308 (The Pile)

Max Activating Token Index: 193

Text #18

Max Range: 0.8530. Min Range: -0.8530

Max Act: 0.6307. Min Act: -0.0000

Data Index: 214605 (The Pile)

Max Activating Token Index: 500

Text #19

Max Range: 0.8530. Min Range: -0.8530

Max Act: 0.6332. Min Act: -0.0000

Data Index: 643550 (The Pile)

Max Activating Token Index: 967