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

Dataset: The Pile

Neuron 1783 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.5897. Min Range: -7.5897

Max Act: 7.5897. Min Act: -0.0000

Data Index: 1530333 (The Pile)

Max Activating Token Index: 86

Text #1

Max Range: 7.5897. Min Range: -7.5897

Max Act: 7.5101. Min Act: -0.0000

Data Index: 774731 (The Pile)

Max Activating Token Index: 223

Text #2

Max Range: 7.5897. Min Range: -7.5897

Max Act: 7.4161. Min Act: -0.0000

Data Index: 941117 (The Pile)

Max Activating Token Index: 143

Text #3

Max Range: 7.5897. Min Range: -7.5897

Max Act: 6.8028. Min Act: -0.0000

Data Index: 532028 (The Pile)

Max Activating Token Index: 171

Text #4

Max Range: 7.5897. Min Range: -7.5897

Max Act: 6.5840. Min Act: -0.0000

Data Index: 831506 (The Pile)

Max Activating Token Index: 68

Text #5

Max Range: 7.5897. Min Range: -7.5897

Max Act: 6.5654. Min Act: -0.0000

Data Index: 983528 (The Pile)

Max Activating Token Index: 900

Text #6

Max Range: 7.5897. Min Range: -7.5897

Max Act: 7.5614. Min Act: -0.0000

Data Index: 1086828 (The Pile)

Max Activating Token Index: 108

Text #7

Max Range: 7.5897. Min Range: -7.5897

Max Act: 7.0812. Min Act: -0.0000

Data Index: 558792 (The Pile)

Max Activating Token Index: 685

Text #8

Max Range: 7.5897. Min Range: -7.5897

Max Act: 6.5413. Min Act: -0.0000

Data Index: 1476350 (The Pile)

Max Activating Token Index: 895

Text #9

Max Range: 7.5897. Min Range: -7.5897

Max Act: 6.3354. Min Act: -0.0000

Data Index: 46317 (The Pile)

Max Activating Token Index: 751

Text #10

Max Range: 7.5897. Min Range: -7.5897

Max Act: 6.3525. Min Act: -0.0000

Data Index: 646537 (The Pile)

Max Activating Token Index: 444

Text #11

Max Range: 7.5897. Min Range: -7.5897

Max Act: 6.1513. Min Act: -0.0000

Data Index: 1946919 (The Pile)

Max Activating Token Index: 170

Text #12

Max Range: 7.5897. Min Range: -7.5897

Max Act: 5.8248. Min Act: -0.0000

Data Index: 168321 (The Pile)

Max Activating Token Index: 891

Text #13

Max Range: 7.5897. Min Range: -7.5897

Max Act: 5.5838. Min Act: -0.0000

Data Index: 1623161 (The Pile)

Max Activating Token Index: 222

Text #14

Max Range: 7.5897. Min Range: -7.5897

Max Act: 4.7367. Min Act: -0.0000

Data Index: 472485 (The Pile)

Max Activating Token Index: 247

Text #15

Max Range: 7.5897. Min Range: -7.5897

Max Act: 5.1897. Min Act: -0.0000

Data Index: 958337 (The Pile)

Max Activating Token Index: 80

Text #16

Max Range: 7.5897. Min Range: -7.5897

Max Act: 5.5554. Min Act: -0.0000

Data Index: 1323715 (The Pile)

Max Activating Token Index: 514

Text #17

Max Range: 7.5897. Min Range: -7.5897

Max Act: 5.8944. Min Act: -0.0000

Data Index: 1422052 (The Pile)

Max Activating Token Index: 788

Text #18

Max Range: 7.5897. Min Range: -7.5897

Max Act: 5.2866. Min Act: -0.0000

Data Index: 986882 (The Pile)

Max Activating Token Index: 259

Text #19

Max Range: 7.5897. Min Range: -7.5897

Max Act: 5.3837. Min Act: -0.0000

Data Index: 1167345 (The Pile)

Max Activating Token Index: 512