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

Dataset: The Pile

Neuron 2457 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: 0.1345. Min Range: -0.1345

Max Act: 0.1345. Min Act: -0.0000

Data Index: 1480052 (The Pile)

Max Activating Token Index: 23

Text #1

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.1144. Min Act: -0.0000

Data Index: 486339 (The Pile)

Max Activating Token Index: 773

Text #2

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.0996. Min Act: -0.0000

Data Index: 394300 (The Pile)

Max Activating Token Index: 596

Text #3

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.0969. Min Act: -0.0000

Data Index: 1757156 (The Pile)

Max Activating Token Index: 391

Text #4

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.1009. Min Act: -0.0000

Data Index: 1815872 (The Pile)

Max Activating Token Index: 561

Text #5

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.0876. Min Act: -0.0000

Data Index: 1012252 (The Pile)

Max Activating Token Index: 144

Text #6

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.0934. Min Act: -0.0000

Data Index: 1307949 (The Pile)

Max Activating Token Index: 185

Text #7

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.0893. Min Act: -0.0000

Data Index: 1602587 (The Pile)

Max Activating Token Index: 619

Text #8

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.0862. Min Act: -0.0000

Data Index: 928080 (The Pile)

Max Activating Token Index: 512

Text #9

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.0946. Min Act: -0.0000

Data Index: 471861 (The Pile)

Max Activating Token Index: 50

Text #10

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.0833. Min Act: -0.0000

Data Index: 568923 (The Pile)

Max Activating Token Index: 36

Text #11

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.0903. Min Act: -0.0000

Data Index: 1831259 (The Pile)

Max Activating Token Index: 65

Text #12

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.0900. Min Act: -0.0000

Data Index: 1692184 (The Pile)

Max Activating Token Index: 288

Text #13

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.0915. Min Act: -0.0000

Data Index: 827427 (The Pile)

Max Activating Token Index: 760

Text #14

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.0893. Min Act: -0.0000

Data Index: 1473772 (The Pile)

Max Activating Token Index: 607

Text #15

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.0878. Min Act: -0.0000

Data Index: 1890765 (The Pile)

Max Activating Token Index: 199

Text #16

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.0800. Min Act: -0.0000

Data Index: 1269058 (The Pile)

Max Activating Token Index: 90

Text #17

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.0797. Min Act: -0.0000

Data Index: 1124985 (The Pile)

Max Activating Token Index: 630

Text #18

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.0836. Min Act: -0.0000

Data Index: 602789 (The Pile)

Max Activating Token Index: 297

Text #19

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.0834. Min Act: -0.0000

Data Index: 1030455 (The Pile)

Max Activating Token Index: 246