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

Dataset: The Pile

Neuron 2638 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7029. Min Range: -0.7029

Max Act: 0.6363. Min Act: -0.0000

Data Index: 701290 (The Pile)

Max Activating Token Index: 579

Text #1

Max Range: 0.7029. Min Range: -0.7029

Max Act: 0.7029. Min Act: -0.0000

Data Index: 775674 (The Pile)

Max Activating Token Index: 882

Text #2

Max Range: 0.7029. Min Range: -0.7029

Max Act: 0.6787. Min Act: -0.0000

Data Index: 1049622 (The Pile)

Max Activating Token Index: 221

Text #3

Max Range: 0.7029. Min Range: -0.7029

Max Act: 0.5671. Min Act: -0.0000

Data Index: 1377808 (The Pile)

Max Activating Token Index: 256

Text #4

Max Range: 0.7029. Min Range: -0.7029

Max Act: 0.5167. Min Act: -0.0000

Data Index: 252626 (The Pile)

Max Activating Token Index: 963

Text #5

Max Range: 0.7029. Min Range: -0.7029

Max Act: 0.6553. Min Act: -0.0000

Data Index: 130685 (The Pile)

Max Activating Token Index: 475

Text #6

Max Range: 0.7029. Min Range: -0.7029

Max Act: 0.5896. Min Act: -0.0000

Data Index: 920326 (The Pile)

Max Activating Token Index: 708

Text #7

Max Range: 0.7029. Min Range: -0.7029

Max Act: 0.6208. Min Act: -0.0000

Data Index: 1129763 (The Pile)

Max Activating Token Index: 490

Text #8

Max Range: 0.7029. Min Range: -0.7029

Max Act: 0.5738. Min Act: -0.0000

Data Index: 977001 (The Pile)

Max Activating Token Index: 13

Text #9

Max Range: 0.7029. Min Range: -0.7029

Max Act: 0.5855. Min Act: -0.0000

Data Index: 485278 (The Pile)

Max Activating Token Index: 157

Text #10

Max Range: 0.7029. Min Range: -0.7029

Max Act: 0.5936. Min Act: -0.0000

Data Index: 1167588 (The Pile)

Max Activating Token Index: 198

Text #11

Max Range: 0.7029. Min Range: -0.7029

Max Act: 0.5530. Min Act: -0.0000

Data Index: 611585 (The Pile)

Max Activating Token Index: 538

Text #12

Max Range: 0.7029. Min Range: -0.7029

Max Act: 0.6976. Min Act: -0.0000

Data Index: 173023 (The Pile)

Max Activating Token Index: 1010

Text #13

Max Range: 0.7029. Min Range: -0.7029

Max Act: 0.5358. Min Act: -0.0000

Data Index: 287149 (The Pile)

Max Activating Token Index: 384

Text #14

Max Range: 0.7029. Min Range: -0.7029

Max Act: 0.5703. Min Act: -0.0000

Data Index: 1376121 (The Pile)

Max Activating Token Index: 506

Text #15

Max Range: 0.7029. Min Range: -0.7029

Max Act: 0.5325. Min Act: -0.0000

Data Index: 1348790 (The Pile)

Max Activating Token Index: 107

Text #16

Max Range: 0.7029. Min Range: -0.7029

Max Act: 0.5160. Min Act: -0.0000

Data Index: 1161446 (The Pile)

Max Activating Token Index: 353

Text #17

Max Range: 0.7029. Min Range: -0.7029

Max Act: 0.5664. Min Act: -0.0000

Data Index: 820179 (The Pile)

Max Activating Token Index: 821

Text #18

Max Range: 0.7029. Min Range: -0.7029

Max Act: 0.5431. Min Act: -0.0000

Data Index: 1198271 (The Pile)

Max Activating Token Index: 256

Text #19

Max Range: 0.7029. Min Range: -0.7029

Max Act: 0.5347. Min Act: -0.0000

Data Index: 1999115 (The Pile)

Max Activating Token Index: 345