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

Dataset: The Pile

Neuron 3828 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5120. Min Range: -0.5120

Max Act: 0.4715. Min Act: -0.0000

Data Index: 1149898 (The Pile)

Max Activating Token Index: 656

Text #1

Max Range: 0.5120. Min Range: -0.5120

Max Act: 0.5120. Min Act: -0.0000

Data Index: 1476420 (The Pile)

Max Activating Token Index: 683

Text #2

Max Range: 0.5120. Min Range: -0.5120

Max Act: 0.4383. Min Act: -0.0000

Data Index: 1124786 (The Pile)

Max Activating Token Index: 287

Text #3

Max Range: 0.5120. Min Range: -0.5120

Max Act: 0.3529. Min Act: -0.0000

Data Index: 118 (The Pile)

Max Activating Token Index: 91

Text #4

Max Range: 0.5120. Min Range: -0.5120

Max Act: 0.3261. Min Act: -0.0000

Data Index: 1564845 (The Pile)

Max Activating Token Index: 115

Text #5

Max Range: 0.5120. Min Range: -0.5120

Max Act: 0.3184. Min Act: -0.0000

Data Index: 943246 (The Pile)

Max Activating Token Index: 148

Text #6

Max Range: 0.5120. Min Range: -0.5120

Max Act: 0.3058. Min Act: -0.0000

Data Index: 1568291 (The Pile)

Max Activating Token Index: 419

Text #7

Max Range: 0.5120. Min Range: -0.5120

Max Act: 0.2896. Min Act: -0.0000

Data Index: 23774 (The Pile)

Max Activating Token Index: 441

Text #8

Max Range: 0.5120. Min Range: -0.5120

Max Act: 0.2891. Min Act: -0.0000

Data Index: 847059 (The Pile)

Max Activating Token Index: 846

Text #9

Max Range: 0.5120. Min Range: -0.5120

Max Act: 0.2990. Min Act: -0.0000

Data Index: 802003 (The Pile)

Max Activating Token Index: 966

Text #10

Max Range: 0.5120. Min Range: -0.5120

Max Act: 0.2565. Min Act: -0.0000

Data Index: 1011593 (The Pile)

Max Activating Token Index: 738

Text #11

Max Range: 0.5120. Min Range: -0.5120

Max Act: 0.2621. Min Act: -0.0000

Data Index: 976634 (The Pile)

Max Activating Token Index: 182

Text #12

Max Range: 0.5120. Min Range: -0.5120

Max Act: 0.2357. Min Act: -0.0000

Data Index: 1573225 (The Pile)

Max Activating Token Index: 548

Text #13

Max Range: 0.5120. Min Range: -0.5120

Max Act: 0.2012. Min Act: -0.0000

Data Index: 1875243 (The Pile)

Max Activating Token Index: 810

Text #14

Max Range: 0.5120. Min Range: -0.5120

Max Act: 0.2480. Min Act: -0.0000

Data Index: 1023845 (The Pile)

Max Activating Token Index: 593

Text #15

Max Range: 0.5120. Min Range: -0.5120

Max Act: 0.2412. Min Act: -0.0000

Data Index: 621045 (The Pile)

Max Activating Token Index: 274

Text #16

Max Range: 0.5120. Min Range: -0.5120

Max Act: 0.2182. Min Act: -0.0000

Data Index: 1601746 (The Pile)

Max Activating Token Index: 996

Text #17

Max Range: 0.5120. Min Range: -0.5120

Max Act: 0.2268. Min Act: -0.0000

Data Index: 1631970 (The Pile)

Max Activating Token Index: 256

Text #18

Max Range: 0.5120. Min Range: -0.5120

Max Act: 0.2247. Min Act: -0.0000

Data Index: 1060504 (The Pile)

Max Activating Token Index: 68

Text #19

Max Range: 0.5120. Min Range: -0.5120

Max Act: 0.2010. Min Act: -0.0000

Data Index: 830834 (The Pile)

Max Activating Token Index: 606