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

Dataset: The Pile

Neuron 2657 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9729. Min Range: -3.9729

Max Act: 3.9729. Min Act: -0.0000

Data Index: 171151 (The Pile)

Max Activating Token Index: 297

Text #1

Max Range: 3.9729. Min Range: -3.9729

Max Act: 3.6510. Min Act: -0.0000

Data Index: 1955865 (The Pile)

Max Activating Token Index: 812

Text #2

Max Range: 3.9729. Min Range: -3.9729

Max Act: 3.5026. Min Act: -0.0000

Data Index: 1954347 (The Pile)

Max Activating Token Index: 444

Text #3

Max Range: 3.9729. Min Range: -3.9729

Max Act: 3.1431. Min Act: -0.0000

Data Index: 1075431 (The Pile)

Max Activating Token Index: 101

Text #4

Max Range: 3.9729. Min Range: -3.9729

Max Act: 3.0037. Min Act: -0.0000

Data Index: 1511091 (The Pile)

Max Activating Token Index: 734

Text #5

Max Range: 3.9729. Min Range: -3.9729

Max Act: 2.7094. Min Act: -0.0000

Data Index: 1403975 (The Pile)

Max Activating Token Index: 447

Text #6

Max Range: 3.9729. Min Range: -3.9729

Max Act: 2.6177. Min Act: -0.0000

Data Index: 1298212 (The Pile)

Max Activating Token Index: 468

Text #7

Max Range: 3.9729. Min Range: -3.9729

Max Act: 2.6537. Min Act: -0.0000

Data Index: 1275026 (The Pile)

Max Activating Token Index: 942

Text #8

Max Range: 3.9729. Min Range: -3.9729

Max Act: 2.5069. Min Act: -0.0000

Data Index: 1937894 (The Pile)

Max Activating Token Index: 665

Text #9

Max Range: 3.9729. Min Range: -3.9729

Max Act: 2.6184. Min Act: -0.0000

Data Index: 1849150 (The Pile)

Max Activating Token Index: 872

Text #10

Max Range: 3.9729. Min Range: -3.9729

Max Act: 2.6098. Min Act: -0.0000

Data Index: 397552 (The Pile)

Max Activating Token Index: 903

Text #11

Max Range: 3.9729. Min Range: -3.9729

Max Act: 2.6217. Min Act: -0.0000

Data Index: 14527 (The Pile)

Max Activating Token Index: 658

Text #12

Max Range: 3.9729. Min Range: -3.9729

Max Act: 2.6099. Min Act: -0.0000

Data Index: 332208 (The Pile)

Max Activating Token Index: 93

Text #13

Max Range: 3.9729. Min Range: -3.9729

Max Act: 2.4720. Min Act: -0.0000

Data Index: 1118070 (The Pile)

Max Activating Token Index: 532

Text #14

Max Range: 3.9729. Min Range: -3.9729

Max Act: 2.6069. Min Act: -0.0000

Data Index: 346137 (The Pile)

Max Activating Token Index: 387

Text #15

Max Range: 3.9729. Min Range: -3.9729

Max Act: 2.6090. Min Act: -0.0000

Data Index: 72635 (The Pile)

Max Activating Token Index: 914

Text #16

Max Range: 3.9729. Min Range: -3.9729

Max Act: 2.4602. Min Act: -0.0000

Data Index: 1095565 (The Pile)

Max Activating Token Index: 475

Text #17

Max Range: 3.9729. Min Range: -3.9729

Max Act: 2.7409. Min Act: -0.0000

Data Index: 1088074 (The Pile)

Max Activating Token Index: 384

Text #18

Max Range: 3.9729. Min Range: -3.9729

Max Act: 2.5752. Min Act: -0.0000

Data Index: 1123078 (The Pile)

Max Activating Token Index: 531

Text #19

Max Range: 3.9729. Min Range: -3.9729

Max Act: 2.4116. Min Act: -0.0000

Data Index: 402823 (The Pile)

Max Activating Token Index: 729