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

Dataset: The Pile

Neuron 4058 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9132. Min Range: -0.9132

Max Act: 0.9132. Min Act: -0.0000

Data Index: 80891 (The Pile)

Max Activating Token Index: 125

Text #1

Max Range: 0.9132. Min Range: -0.9132

Max Act: 0.8265. Min Act: -0.0000

Data Index: 4411 (The Pile)

Max Activating Token Index: 198

Text #2

Max Range: 0.9132. Min Range: -0.9132

Max Act: 0.8623. Min Act: -0.0000

Data Index: 253505 (The Pile)

Max Activating Token Index: 316

Text #3

Max Range: 0.9132. Min Range: -0.9132

Max Act: 0.7776. Min Act: -0.0000

Data Index: 686865 (The Pile)

Max Activating Token Index: 772

Text #4

Max Range: 0.9132. Min Range: -0.9132

Max Act: 0.7615. Min Act: -0.0000

Data Index: 1414090 (The Pile)

Max Activating Token Index: 318

Text #5

Max Range: 0.9132. Min Range: -0.9132

Max Act: 0.7209. Min Act: -0.0000

Data Index: 591992 (The Pile)

Max Activating Token Index: 441

Text #6

Max Range: 0.9132. Min Range: -0.9132

Max Act: 0.6752. Min Act: -0.0000

Data Index: 1622859 (The Pile)

Max Activating Token Index: 81

Text #7

Max Range: 0.9132. Min Range: -0.9132

Max Act: 0.7043. Min Act: -0.0000

Data Index: 1421066 (The Pile)

Max Activating Token Index: 193

Text #8

Max Range: 0.9132. Min Range: -0.9132

Max Act: 0.6474. Min Act: -0.0000

Data Index: 219873 (The Pile)

Max Activating Token Index: 265

Text #9

Max Range: 0.9132. Min Range: -0.9132

Max Act: 0.6679. Min Act: -0.0000

Data Index: 1022774 (The Pile)

Max Activating Token Index: 780

Text #10

Max Range: 0.9132. Min Range: -0.9132

Max Act: 0.6698. Min Act: -0.0000

Data Index: 1803814 (The Pile)

Max Activating Token Index: 506

Text #11

Max Range: 0.9132. Min Range: -0.9132

Max Act: 0.6442. Min Act: -0.0000

Data Index: 1942700 (The Pile)

Max Activating Token Index: 326

Text #12

Max Range: 0.9132. Min Range: -0.9132

Max Act: 0.5982. Min Act: -0.0000

Data Index: 1773584 (The Pile)

Max Activating Token Index: 457

Text #13

Max Range: 0.9132. Min Range: -0.9132

Max Act: 0.5476. Min Act: -0.0000

Data Index: 763926 (The Pile)

Max Activating Token Index: 721

Text #14

Max Range: 0.9132. Min Range: -0.9132

Max Act: 0.5730. Min Act: -0.0000

Data Index: 1582492 (The Pile)

Max Activating Token Index: 707

Text #15

Max Range: 0.9132. Min Range: -0.9132

Max Act: 0.6148. Min Act: -0.0000

Data Index: 1120073 (The Pile)

Max Activating Token Index: 293

Text #16

Max Range: 0.9132. Min Range: -0.9132

Max Act: 0.5410. Min Act: -0.0000

Data Index: 635965 (The Pile)

Max Activating Token Index: 524

Text #17

Max Range: 0.9132. Min Range: -0.9132

Max Act: 0.5657. Min Act: -0.0000

Data Index: 1183369 (The Pile)

Max Activating Token Index: 256

Text #18

Max Range: 0.9132. Min Range: -0.9132

Max Act: 0.5500. Min Act: -0.0000

Data Index: 1152979 (The Pile)

Max Activating Token Index: 910

Text #19

Max Range: 0.9132. Min Range: -0.9132

Max Act: 0.4859. Min Act: -0.0000

Data Index: 331172 (The Pile)

Max Activating Token Index: 858