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

Dataset: The Pile

Neuron 3742 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8279. Min Range: -0.8279

Max Act: 0.8279. Min Act: -0.0000

Data Index: 1298610 (The Pile)

Max Activating Token Index: 888

Text #1

Max Range: 0.8279. Min Range: -0.8279

Max Act: 0.7088. Min Act: -0.0000

Data Index: 1301342 (The Pile)

Max Activating Token Index: 552

Text #2

Max Range: 0.8279. Min Range: -0.8279

Max Act: 0.7338. Min Act: -0.0000

Data Index: 1780038 (The Pile)

Max Activating Token Index: 533

Text #3

Max Range: 0.8279. Min Range: -0.8279

Max Act: 0.6787. Min Act: -0.0000

Data Index: 1769465 (The Pile)

Max Activating Token Index: 355

Text #4

Max Range: 0.8279. Min Range: -0.8279

Max Act: 0.6503. Min Act: -0.0000

Data Index: 83856 (The Pile)

Max Activating Token Index: 188

Text #5

Max Range: 0.8279. Min Range: -0.8279

Max Act: 0.6676. Min Act: -0.0000

Data Index: 1741970 (The Pile)

Max Activating Token Index: 779

Text #6

Max Range: 0.8279. Min Range: -0.8279

Max Act: 0.6332. Min Act: -0.0000

Data Index: 1527645 (The Pile)

Max Activating Token Index: 479

Text #7

Max Range: 0.8279. Min Range: -0.8279

Max Act: 0.6515. Min Act: -0.0000

Data Index: 975162 (The Pile)

Max Activating Token Index: 507

Text #8

Max Range: 0.8279. Min Range: -0.8279

Max Act: 0.6717. Min Act: -0.0000

Data Index: 7749 (The Pile)

Max Activating Token Index: 413

Text #9

Max Range: 0.8279. Min Range: -0.8279

Max Act: 0.6445. Min Act: -0.0000

Data Index: 1960564 (The Pile)

Max Activating Token Index: 298

Text #10

Max Range: 0.8279. Min Range: -0.8279

Max Act: 0.6278. Min Act: -0.0000

Data Index: 933792 (The Pile)

Max Activating Token Index: 399

Text #11

Max Range: 0.8279. Min Range: -0.8279

Max Act: 0.5727. Min Act: -0.0000

Data Index: 1999907 (The Pile)

Max Activating Token Index: 706

Text #12

Max Range: 0.8279. Min Range: -0.8279

Max Act: 0.6397. Min Act: -0.0000

Data Index: 746691 (The Pile)

Max Activating Token Index: 88

Text #13

Max Range: 0.8279. Min Range: -0.8279

Max Act: 0.6381. Min Act: -0.0000

Data Index: 1612373 (The Pile)

Max Activating Token Index: 7

Text #14

Max Range: 0.8279. Min Range: -0.8279

Max Act: 0.5895. Min Act: -0.0000

Data Index: 1978053 (The Pile)

Max Activating Token Index: 891

Text #15

Max Range: 0.8279. Min Range: -0.8279

Max Act: 0.6050. Min Act: -0.0000

Data Index: 196072 (The Pile)

Max Activating Token Index: 769

Text #16

Max Range: 0.8279. Min Range: -0.8279

Max Act: 0.5812. Min Act: -0.0000

Data Index: 946520 (The Pile)

Max Activating Token Index: 331

Text #17

Max Range: 0.8279. Min Range: -0.8279

Max Act: 0.5927. Min Act: -0.0000

Data Index: 274809 (The Pile)

Max Activating Token Index: 819

Text #18

Max Range: 0.8279. Min Range: -0.8279

Max Act: 0.6156. Min Act: -0.0000

Data Index: 827650 (The Pile)

Max Activating Token Index: 3

Text #19

Max Range: 0.8279. Min Range: -0.8279

Max Act: 0.5933. Min Act: -0.0000

Data Index: 479090 (The Pile)

Max Activating Token Index: 392