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

Dataset: The Pile

Neuron 586 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: 1.0897. Min Range: -1.0897

Max Act: 1.0897. Min Act: -0.0000

Data Index: 230335 (The Pile)

Max Activating Token Index: 837

Text #1

Max Range: 1.0897. Min Range: -1.0897

Max Act: 0.9911. Min Act: -0.0000

Data Index: 1592585 (The Pile)

Max Activating Token Index: 562

Text #2

Max Range: 1.0897. Min Range: -1.0897

Max Act: 1.0295. Min Act: -0.0000

Data Index: 1107405 (The Pile)

Max Activating Token Index: 495

Text #3

Max Range: 1.0897. Min Range: -1.0897

Max Act: 0.9657. Min Act: -0.0000

Data Index: 1218959 (The Pile)

Max Activating Token Index: 183

Text #4

Max Range: 1.0897. Min Range: -1.0897

Max Act: 0.9870. Min Act: -0.0000

Data Index: 1376684 (The Pile)

Max Activating Token Index: 479

Text #5

Max Range: 1.0897. Min Range: -1.0897

Max Act: 0.9529. Min Act: -0.0000

Data Index: 849406 (The Pile)

Max Activating Token Index: 954

Text #6

Max Range: 1.0897. Min Range: -1.0897

Max Act: 1.0179. Min Act: -0.0000

Data Index: 1844747 (The Pile)

Max Activating Token Index: 687

Text #7

Max Range: 1.0897. Min Range: -1.0897

Max Act: 0.9841. Min Act: -0.0000

Data Index: 1971474 (The Pile)

Max Activating Token Index: 255

Text #8

Max Range: 1.0897. Min Range: -1.0897

Max Act: 0.9386. Min Act: -0.0000

Data Index: 1544870 (The Pile)

Max Activating Token Index: 863

Text #9

Max Range: 1.0897. Min Range: -1.0897

Max Act: 0.9111. Min Act: -0.0000

Data Index: 1719863 (The Pile)

Max Activating Token Index: 696

Text #10

Max Range: 1.0897. Min Range: -1.0897

Max Act: 0.9796. Min Act: -0.0000

Data Index: 1681109 (The Pile)

Max Activating Token Index: 202

Text #11

Max Range: 1.0897. Min Range: -1.0897

Max Act: 0.8983. Min Act: -0.0000

Data Index: 945220 (The Pile)

Max Activating Token Index: 51

Text #12

Max Range: 1.0897. Min Range: -1.0897

Max Act: 0.8592. Min Act: -0.0000

Data Index: 820864 (The Pile)

Max Activating Token Index: 973

Text #13

Max Range: 1.0897. Min Range: -1.0897

Max Act: 0.9109. Min Act: -0.0000

Data Index: 1519802 (The Pile)

Max Activating Token Index: 365

Text #14

Max Range: 1.0897. Min Range: -1.0897

Max Act: 0.9119. Min Act: -0.0000

Data Index: 66293 (The Pile)

Max Activating Token Index: 726

Text #15

Max Range: 1.0897. Min Range: -1.0897

Max Act: 0.8954. Min Act: -0.0000

Data Index: 1637333 (The Pile)

Max Activating Token Index: 208

Text #16

Max Range: 1.0897. Min Range: -1.0897

Max Act: 0.8731. Min Act: -0.0000

Data Index: 1173662 (The Pile)

Max Activating Token Index: 153

Text #17

Max Range: 1.0897. Min Range: -1.0897

Max Act: 0.9012. Min Act: -0.0000

Data Index: 1791015 (The Pile)

Max Activating Token Index: 519

Text #18

Max Range: 1.0897. Min Range: -1.0897

Max Act: 0.8941. Min Act: -0.0000

Data Index: 83822 (The Pile)

Max Activating Token Index: 140

Text #19

Max Range: 1.0897. Min Range: -1.0897

Max Act: 0.8457. Min Act: -0.0000

Data Index: 1184364 (The Pile)

Max Activating Token Index: 154