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

Dataset: The Pile

Neuron 1815 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6136. Min Range: -3.6136

Max Act: 3.6136. Min Act: -0.0000

Data Index: 1633637 (The Pile)

Max Activating Token Index: 1003

Text #1

Max Range: 3.6136. Min Range: -3.6136

Max Act: 3.0318. Min Act: -0.0000

Data Index: 886198 (The Pile)

Max Activating Token Index: 364

Text #2

Max Range: 3.6136. Min Range: -3.6136

Max Act: 3.1960. Min Act: -0.0000

Data Index: 1281900 (The Pile)

Max Activating Token Index: 869

Text #3

Max Range: 3.6136. Min Range: -3.6136

Max Act: 2.9118. Min Act: -0.0000

Data Index: 134806 (The Pile)

Max Activating Token Index: 144

Text #4

Max Range: 3.6136. Min Range: -3.6136

Max Act: 3.0871. Min Act: -0.0000

Data Index: 1396810 (The Pile)

Max Activating Token Index: 945

Text #5

Max Range: 3.6136. Min Range: -3.6136

Max Act: 2.4121. Min Act: -0.0000

Data Index: 524155 (The Pile)

Max Activating Token Index: 781

Text #6

Max Range: 3.6136. Min Range: -3.6136

Max Act: 2.8971. Min Act: -0.0000

Data Index: 558269 (The Pile)

Max Activating Token Index: 794

Text #7

Max Range: 3.6136. Min Range: -3.6136

Max Act: 2.1169. Min Act: -0.0000

Data Index: 768377 (The Pile)

Max Activating Token Index: 928

Text #8

Max Range: 3.6136. Min Range: -3.6136

Max Act: 2.0607. Min Act: -0.0000

Data Index: 430941 (The Pile)

Max Activating Token Index: 522

Text #9

Max Range: 3.6136. Min Range: -3.6136

Max Act: 2.5277. Min Act: -0.0000

Data Index: 480177 (The Pile)

Max Activating Token Index: 530

Text #10

Max Range: 3.6136. Min Range: -3.6136

Max Act: 2.6440. Min Act: -0.0000

Data Index: 1212006 (The Pile)

Max Activating Token Index: 1006

Text #11

Max Range: 3.6136. Min Range: -3.6136

Max Act: 2.3554. Min Act: -0.0000

Data Index: 585367 (The Pile)

Max Activating Token Index: 802

Text #12

Max Range: 3.6136. Min Range: -3.6136

Max Act: 2.0846. Min Act: -0.0000

Data Index: 1617087 (The Pile)

Max Activating Token Index: 578

Text #13

Max Range: 3.6136. Min Range: -3.6136

Max Act: 2.3629. Min Act: -0.0000

Data Index: 1046436 (The Pile)

Max Activating Token Index: 453

Text #14

Max Range: 3.6136. Min Range: -3.6136

Max Act: 2.2168. Min Act: -0.0000

Data Index: 1196138 (The Pile)

Max Activating Token Index: 409

Text #15

Max Range: 3.6136. Min Range: -3.6136

Max Act: 2.1060. Min Act: -0.0000

Data Index: 913376 (The Pile)

Max Activating Token Index: 417

Text #16

Max Range: 3.6136. Min Range: -3.6136

Max Act: 1.7291. Min Act: -0.0000

Data Index: 1063656 (The Pile)

Max Activating Token Index: 72

Text #17

Max Range: 3.6136. Min Range: -3.6136

Max Act: 2.2031. Min Act: -0.0000

Data Index: 983542 (The Pile)

Max Activating Token Index: 271

Text #18

Max Range: 3.6136. Min Range: -3.6136

Max Act: 2.5498. Min Act: -0.0000

Data Index: 347044 (The Pile)

Max Activating Token Index: 853

Text #19

Max Range: 3.6136. Min Range: -3.6136

Max Act: 1.9876. Min Act: -0.0000

Data Index: 1291579 (The Pile)

Max Activating Token Index: 669