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

Dataset: The Pile

Neuron 3747 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: 1.0107. Min Range: -1.0107

Max Act: 1.0107. Min Act: -0.0000

Data Index: 1855826 (The Pile)

Max Activating Token Index: 316

Text #1

Max Range: 1.0107. Min Range: -1.0107

Max Act: 0.9751. Min Act: -0.0000

Data Index: 1027642 (The Pile)

Max Activating Token Index: 269

Text #2

Max Range: 1.0107. Min Range: -1.0107

Max Act: 0.9826. Min Act: -0.0000

Data Index: 1923638 (The Pile)

Max Activating Token Index: 463

Text #3

Max Range: 1.0107. Min Range: -1.0107

Max Act: 0.9227. Min Act: -0.0000

Data Index: 1351365 (The Pile)

Max Activating Token Index: 269

Text #4

Max Range: 1.0107. Min Range: -1.0107

Max Act: 0.9009. Min Act: -0.0000

Data Index: 487579 (The Pile)

Max Activating Token Index: 878

Text #5

Max Range: 1.0107. Min Range: -1.0107

Max Act: 0.8788. Min Act: -0.0000

Data Index: 759864 (The Pile)

Max Activating Token Index: 63

Text #6

Max Range: 1.0107. Min Range: -1.0107

Max Act: 0.8907. Min Act: -0.0000

Data Index: 1607025 (The Pile)

Max Activating Token Index: 791

Text #7

Max Range: 1.0107. Min Range: -1.0107

Max Act: 0.9189. Min Act: -0.0000

Data Index: 444945 (The Pile)

Max Activating Token Index: 22

Text #8

Max Range: 1.0107. Min Range: -1.0107

Max Act: 0.8978. Min Act: -0.0000

Data Index: 1926920 (The Pile)

Max Activating Token Index: 309

Text #9

Max Range: 1.0107. Min Range: -1.0107

Max Act: 0.8624. Min Act: -0.0000

Data Index: 296254 (The Pile)

Max Activating Token Index: 953

Text #10

Max Range: 1.0107. Min Range: -1.0107

Max Act: 0.8327. Min Act: -0.0000

Data Index: 554076 (The Pile)

Max Activating Token Index: 342

Text #11

Max Range: 1.0107. Min Range: -1.0107

Max Act: 0.8287. Min Act: -0.0000

Data Index: 1048402 (The Pile)

Max Activating Token Index: 147

Text #12

Max Range: 1.0107. Min Range: -1.0107

Max Act: 0.8446. Min Act: -0.0000

Data Index: 303325 (The Pile)

Max Activating Token Index: 424

Text #13

Max Range: 1.0107. Min Range: -1.0107

Max Act: 0.8487. Min Act: -0.0000

Data Index: 1514177 (The Pile)

Max Activating Token Index: 1018

Text #14

Max Range: 1.0107. Min Range: -1.0107

Max Act: 0.8136. Min Act: -0.0000

Data Index: 1662027 (The Pile)

Max Activating Token Index: 521

Text #15

Max Range: 1.0107. Min Range: -1.0107

Max Act: 0.7734. Min Act: -0.0000

Data Index: 711403 (The Pile)

Max Activating Token Index: 115

Text #16

Max Range: 1.0107. Min Range: -1.0107

Max Act: 0.7941. Min Act: -0.0000

Data Index: 941853 (The Pile)

Max Activating Token Index: 129

Text #17

Max Range: 1.0107. Min Range: -1.0107

Max Act: 0.7679. Min Act: -0.0000

Data Index: 1454900 (The Pile)

Max Activating Token Index: 282

Text #18

Max Range: 1.0107. Min Range: -1.0107

Max Act: 0.7576. Min Act: -0.0000

Data Index: 1961650 (The Pile)

Max Activating Token Index: 939

Text #19

Max Range: 1.0107. Min Range: -1.0107

Max Act: 0.7883. Min Act: -0.0000

Data Index: 1877895 (The Pile)

Max Activating Token Index: 230