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

Dataset: The Pile

Neuron 2472 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5560. Min Range: -0.5560

Max Act: 0.5560. Min Act: -0.0000

Data Index: 1913120 (The Pile)

Max Activating Token Index: 258

Text #1

Max Range: 0.5560. Min Range: -0.5560

Max Act: 0.5298. Min Act: -0.0000

Data Index: 396271 (The Pile)

Max Activating Token Index: 929

Text #2

Max Range: 0.5560. Min Range: -0.5560

Max Act: 0.5280. Min Act: -0.0000

Data Index: 1838537 (The Pile)

Max Activating Token Index: 287

Text #3

Max Range: 0.5560. Min Range: -0.5560

Max Act: 0.4319. Min Act: -0.0000

Data Index: 560965 (The Pile)

Max Activating Token Index: 688

Text #4

Max Range: 0.5560. Min Range: -0.5560

Max Act: 0.4413. Min Act: -0.0000

Data Index: 1099805 (The Pile)

Max Activating Token Index: 187

Text #5

Max Range: 0.5560. Min Range: -0.5560

Max Act: 0.4158. Min Act: -0.0000

Data Index: 694058 (The Pile)

Max Activating Token Index: 629

Text #6

Max Range: 0.5560. Min Range: -0.5560

Max Act: 0.3887. Min Act: -0.0000

Data Index: 1165569 (The Pile)

Max Activating Token Index: 649

Text #7

Max Range: 0.5560. Min Range: -0.5560

Max Act: 0.4128. Min Act: -0.0000

Data Index: 1463611 (The Pile)

Max Activating Token Index: 397

Text #8

Max Range: 0.5560. Min Range: -0.5560

Max Act: 0.4219. Min Act: -0.0000

Data Index: 1187496 (The Pile)

Max Activating Token Index: 582

Text #9

Max Range: 0.5560. Min Range: -0.5560

Max Act: 0.4109. Min Act: -0.0000

Data Index: 307976 (The Pile)

Max Activating Token Index: 418

Text #10

Max Range: 0.5560. Min Range: -0.5560

Max Act: 0.4258. Min Act: -0.0000

Data Index: 99738 (The Pile)

Max Activating Token Index: 210

Text #11

Max Range: 0.5560. Min Range: -0.5560

Max Act: 0.4098. Min Act: -0.0000

Data Index: 1390222 (The Pile)

Max Activating Token Index: 713

Text #12

Max Range: 0.5560. Min Range: -0.5560

Max Act: 0.3778. Min Act: -0.0000

Data Index: 549889 (The Pile)

Max Activating Token Index: 753

Text #13

Max Range: 0.5560. Min Range: -0.5560

Max Act: 0.4141. Min Act: -0.0000

Data Index: 1884264 (The Pile)

Max Activating Token Index: 538

Text #14

Max Range: 0.5560. Min Range: -0.5560

Max Act: 0.4090. Min Act: -0.0000

Data Index: 1257595 (The Pile)

Max Activating Token Index: 123

Text #15

Max Range: 0.5560. Min Range: -0.5560

Max Act: 0.3910. Min Act: -0.0000

Data Index: 1706885 (The Pile)

Max Activating Token Index: 279

Text #16

Max Range: 0.5560. Min Range: -0.5560

Max Act: 0.3767. Min Act: -0.0000

Data Index: 1839180 (The Pile)

Max Activating Token Index: 509

Text #17

Max Range: 0.5560. Min Range: -0.5560

Max Act: 0.3974. Min Act: -0.0000

Data Index: 1108508 (The Pile)

Max Activating Token Index: 334

Text #18

Max Range: 0.5560. Min Range: -0.5560

Max Act: 0.3933. Min Act: -0.0000

Data Index: 1208207 (The Pile)

Max Activating Token Index: 38

Text #19

Max Range: 0.5560. Min Range: -0.5560

Max Act: 0.3764. Min Act: -0.0000

Data Index: 1873598 (The Pile)

Max Activating Token Index: 520