Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 709 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.7809. Min Range: -0.7809

Max Act: 0.7809. Min Act: -0.0000

Data Index: 247423 (The Pile)

Max Activating Token Index: 322

Text #1

Max Range: 0.7809. Min Range: -0.7809

Max Act: 0.6264. Min Act: -0.0000

Data Index: 1058342 (The Pile)

Max Activating Token Index: 164

Text #2

Max Range: 0.7809. Min Range: -0.7809

Max Act: 0.6361. Min Act: -0.0000

Data Index: 1031558 (The Pile)

Max Activating Token Index: 458

Text #3

Max Range: 0.7809. Min Range: -0.7809

Max Act: 0.5930. Min Act: -0.0000

Data Index: 224630 (The Pile)

Max Activating Token Index: 547

Text #4

Max Range: 0.7809. Min Range: -0.7809

Max Act: 0.6136. Min Act: -0.0000

Data Index: 1834758 (The Pile)

Max Activating Token Index: 327

Text #5

Max Range: 0.7809. Min Range: -0.7809

Max Act: 0.5859. Min Act: -0.0000

Data Index: 1000227 (The Pile)

Max Activating Token Index: 854

Text #6

Max Range: 0.7809. Min Range: -0.7809

Max Act: 0.5379. Min Act: -0.0000

Data Index: 498033 (The Pile)

Max Activating Token Index: 260

Text #7

Max Range: 0.7809. Min Range: -0.7809

Max Act: 0.6141. Min Act: -0.0000

Data Index: 231393 (The Pile)

Max Activating Token Index: 672

Text #8

Max Range: 0.7809. Min Range: -0.7809

Max Act: 0.5422. Min Act: -0.0000

Data Index: 1781170 (The Pile)

Max Activating Token Index: 245

Text #9

Max Range: 0.7809. Min Range: -0.7809

Max Act: 0.5583. Min Act: -0.0000

Data Index: 755127 (The Pile)

Max Activating Token Index: 826

Text #10

Max Range: 0.7809. Min Range: -0.7809

Max Act: 0.5213. Min Act: -0.0000

Data Index: 1226302 (The Pile)

Max Activating Token Index: 179

Text #11

Max Range: 0.7809. Min Range: -0.7809

Max Act: 0.5045. Min Act: -0.0000

Data Index: 464349 (The Pile)

Max Activating Token Index: 499

Text #12

Max Range: 0.7809. Min Range: -0.7809

Max Act: 0.4666. Min Act: -0.0000

Data Index: 983337 (The Pile)

Max Activating Token Index: 480

Text #13

Max Range: 0.7809. Min Range: -0.7809

Max Act: 0.5310. Min Act: -0.0000

Data Index: 1435198 (The Pile)

Max Activating Token Index: 300

Text #14

Max Range: 0.7809. Min Range: -0.7809

Max Act: 0.5032. Min Act: -0.0000

Data Index: 1485202 (The Pile)

Max Activating Token Index: 735

Text #15

Max Range: 0.7809. Min Range: -0.7809

Max Act: 0.5026. Min Act: -0.0000

Data Index: 1354915 (The Pile)

Max Activating Token Index: 849

Text #16

Max Range: 0.7809. Min Range: -0.7809

Max Act: 0.4538. Min Act: -0.0000

Data Index: 1175216 (The Pile)

Max Activating Token Index: 152

Text #17

Max Range: 0.7809. Min Range: -0.7809

Max Act: 0.4290. Min Act: -0.0000

Data Index: 908482 (The Pile)

Max Activating Token Index: 741

Text #18

Max Range: 0.7809. Min Range: -0.7809

Max Act: 0.4576. Min Act: -0.0000

Data Index: 225966 (The Pile)

Max Activating Token Index: 503

Text #19

Max Range: 0.7809. Min Range: -0.7809

Max Act: 0.4459. Min Act: -0.0000

Data Index: 516207 (The Pile)

Max Activating Token Index: 248