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

Dataset: The Pile

Neuron 1229 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.8022. Min Range: -0.8022

Max Act: 0.8022. Min Act: -0.0000

Data Index: 247379 (The Pile)

Max Activating Token Index: 617

Text #1

Max Range: 0.8022. Min Range: -0.8022

Max Act: 0.6514. Min Act: -0.0000

Data Index: 73081 (The Pile)

Max Activating Token Index: 443

Text #2

Max Range: 0.8022. Min Range: -0.8022

Max Act: 0.5991. Min Act: 0.0000

Data Index: 707948 (The Pile)

Max Activating Token Index: 763

Text #3

Max Range: 0.8022. Min Range: -0.8022

Max Act: 0.6719. Min Act: -0.0000

Data Index: 64328 (The Pile)

Max Activating Token Index: 634

Text #4

Max Range: 0.8022. Min Range: -0.8022

Max Act: 0.5681. Min Act: -0.0000

Data Index: 664663 (The Pile)

Max Activating Token Index: 1017

Text #5

Max Range: 0.8022. Min Range: -0.8022

Max Act: 0.5962. Min Act: -0.0000

Data Index: 1544448 (The Pile)

Max Activating Token Index: 145

Text #6

Max Range: 0.8022. Min Range: -0.8022

Max Act: 0.5800. Min Act: 0.0000

Data Index: 27830 (The Pile)

Max Activating Token Index: 595

Text #7

Max Range: 0.8022. Min Range: -0.8022

Max Act: 0.5716. Min Act: -0.0000

Data Index: 240790 (The Pile)

Max Activating Token Index: 837

Text #8

Max Range: 0.8022. Min Range: -0.8022

Max Act: 0.5877. Min Act: -0.0000

Data Index: 1312767 (The Pile)

Max Activating Token Index: 776

Text #9

Max Range: 0.8022. Min Range: -0.8022

Max Act: 0.5307. Min Act: 0.0000

Data Index: 1467152 (The Pile)

Max Activating Token Index: 287

Text #10

Max Range: 0.8022. Min Range: -0.8022

Max Act: 0.5136. Min Act: 0.0000

Data Index: 1274648 (The Pile)

Max Activating Token Index: 774

Text #11

Max Range: 0.8022. Min Range: -0.8022

Max Act: 0.5203. Min Act: -0.0000

Data Index: 1449271 (The Pile)

Max Activating Token Index: 1016

Text #12

Max Range: 0.8022. Min Range: -0.8022

Max Act: 0.5212. Min Act: -0.0000

Data Index: 1768924 (The Pile)

Max Activating Token Index: 415

Text #13

Max Range: 0.8022. Min Range: -0.8022

Max Act: 0.5103. Min Act: -0.0000

Data Index: 1715451 (The Pile)

Max Activating Token Index: 223

Text #14

Max Range: 0.8022. Min Range: -0.8022

Max Act: 0.5132. Min Act: -0.0000

Data Index: 576533 (The Pile)

Max Activating Token Index: 152

Text #15

Max Range: 0.8022. Min Range: -0.8022

Max Act: 0.4928. Min Act: -0.0000

Data Index: 1583199 (The Pile)

Max Activating Token Index: 285

Text #16

Max Range: 0.8022. Min Range: -0.8022

Max Act: 0.4950. Min Act: -0.0000

Data Index: 822345 (The Pile)

Max Activating Token Index: 172

Text #17

Max Range: 0.8022. Min Range: -0.8022

Max Act: 0.5270. Min Act: -0.0000

Data Index: 1842524 (The Pile)

Max Activating Token Index: 229

Text #18

Max Range: 0.8022. Min Range: -0.8022

Max Act: 0.4429. Min Act: -0.0000

Data Index: 1218171 (The Pile)

Max Activating Token Index: 546

Text #19

Max Range: 0.8022. Min Range: -0.8022

Max Act: 0.5265. Min Act: -0.0000

Data Index: 1273202 (The Pile)

Max Activating Token Index: 360