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

Dataset: The Pile

Neuron 1604 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: 3.8090. Min Range: -3.8090

Max Act: 3.8090. Min Act: -0.0000

Data Index: 288900 (The Pile)

Max Activating Token Index: 738

Text #1

Max Range: 3.8090. Min Range: -3.8090

Max Act: 3.6309. Min Act: -0.0000

Data Index: 875634 (The Pile)

Max Activating Token Index: 292

Text #2

Max Range: 3.8090. Min Range: -3.8090

Max Act: 3.6132. Min Act: -0.0000

Data Index: 266410 (The Pile)

Max Activating Token Index: 592

Text #3

Max Range: 3.8090. Min Range: -3.8090

Max Act: 3.5433. Min Act: -0.0000

Data Index: 99292 (The Pile)

Max Activating Token Index: 383

Text #4

Max Range: 3.8090. Min Range: -3.8090

Max Act: 3.7029. Min Act: -0.0000

Data Index: 1460224 (The Pile)

Max Activating Token Index: 301

Text #5

Max Range: 3.8090. Min Range: -3.8090

Max Act: 3.6188. Min Act: -0.0000

Data Index: 813575 (The Pile)

Max Activating Token Index: 206

Text #6

Max Range: 3.8090. Min Range: -3.8090

Max Act: 3.4928. Min Act: -0.0000

Data Index: 236373 (The Pile)

Max Activating Token Index: 216

Text #7

Max Range: 3.8090. Min Range: -3.8090

Max Act: 3.1868. Min Act: -0.0000

Data Index: 692617 (The Pile)

Max Activating Token Index: 915

Text #8

Max Range: 3.8090. Min Range: -3.8090

Max Act: 3.1795. Min Act: -0.0000

Data Index: 1796050 (The Pile)

Max Activating Token Index: 860

Text #9

Max Range: 3.8090. Min Range: -3.8090

Max Act: 3.2798. Min Act: -0.0000

Data Index: 1263834 (The Pile)

Max Activating Token Index: 582

Text #10

Max Range: 3.8090. Min Range: -3.8090

Max Act: 3.1092. Min Act: -0.0000

Data Index: 43386 (The Pile)

Max Activating Token Index: 267

Text #11

Max Range: 3.8090. Min Range: -3.8090

Max Act: 3.2379. Min Act: -0.0000

Data Index: 1121617 (The Pile)

Max Activating Token Index: 354

Text #12

Max Range: 3.8090. Min Range: -3.8090

Max Act: 3.0824. Min Act: -0.0000

Data Index: 1256025 (The Pile)

Max Activating Token Index: 467

Text #13

Max Range: 3.8090. Min Range: -3.8090

Max Act: 3.2057. Min Act: -0.0000

Data Index: 1998847 (The Pile)

Max Activating Token Index: 782

Text #14

Max Range: 3.8090. Min Range: -3.8090

Max Act: 2.9836. Min Act: -0.0000

Data Index: 1434665 (The Pile)

Max Activating Token Index: 900

Text #15

Max Range: 3.8090. Min Range: -3.8090

Max Act: 3.2668. Min Act: -0.0000

Data Index: 1474803 (The Pile)

Max Activating Token Index: 62

Text #16

Max Range: 3.8090. Min Range: -3.8090

Max Act: 3.0909. Min Act: -0.0000

Data Index: 1761750 (The Pile)

Max Activating Token Index: 359

Text #17

Max Range: 3.8090. Min Range: -3.8090

Max Act: 3.2545. Min Act: -0.0000

Data Index: 1498925 (The Pile)

Max Activating Token Index: 193

Text #18

Max Range: 3.8090. Min Range: -3.8090

Max Act: 3.0756. Min Act: -0.0000

Data Index: 1496030 (The Pile)

Max Activating Token Index: 115

Text #19

Max Range: 3.8090. Min Range: -3.8090

Max Act: 3.0318. Min Act: -0.0000

Data Index: 469177 (The Pile)

Max Activating Token Index: 442