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

Dataset: The Pile

Neuron 1799 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: 0.8217. Min Range: -0.8217

Max Act: 0.8217. Min Act: -0.0000

Data Index: 1003269 (The Pile)

Max Activating Token Index: 957

Text #1

Max Range: 0.8217. Min Range: -0.8217

Max Act: 0.7653. Min Act: -0.0000

Data Index: 826612 (The Pile)

Max Activating Token Index: 568

Text #2

Max Range: 0.8217. Min Range: -0.8217

Max Act: 0.6672. Min Act: -0.0000

Data Index: 333696 (The Pile)

Max Activating Token Index: 143

Text #3

Max Range: 0.8217. Min Range: -0.8217

Max Act: 0.6262. Min Act: -0.0000

Data Index: 147461 (The Pile)

Max Activating Token Index: 894

Text #4

Max Range: 0.8217. Min Range: -0.8217

Max Act: 0.6581. Min Act: -0.0000

Data Index: 999592 (The Pile)

Max Activating Token Index: 397

Text #5

Max Range: 0.8217. Min Range: -0.8217

Max Act: 0.6525. Min Act: -0.0000

Data Index: 501223 (The Pile)

Max Activating Token Index: 160

Text #6

Max Range: 0.8217. Min Range: -0.8217

Max Act: 0.6288. Min Act: -0.0000

Data Index: 715768 (The Pile)

Max Activating Token Index: 836

Text #7

Max Range: 0.8217. Min Range: -0.8217

Max Act: 0.6744. Min Act: -0.0000

Data Index: 1860099 (The Pile)

Max Activating Token Index: 639

Text #8

Max Range: 0.8217. Min Range: -0.8217

Max Act: 0.5506. Min Act: -0.0000

Data Index: 1768435 (The Pile)

Max Activating Token Index: 58

Text #9

Max Range: 0.8217. Min Range: -0.8217

Max Act: 0.6581. Min Act: -0.0000

Data Index: 765521 (The Pile)

Max Activating Token Index: 92

Text #10

Max Range: 0.8217. Min Range: -0.8217

Max Act: 0.5666. Min Act: -0.0000

Data Index: 1326046 (The Pile)

Max Activating Token Index: 913

Text #11

Max Range: 0.8217. Min Range: -0.8217

Max Act: 0.6057. Min Act: -0.0000

Data Index: 348248 (The Pile)

Max Activating Token Index: 339

Text #12

Max Range: 0.8217. Min Range: -0.8217

Max Act: 0.4408. Min Act: -0.0000

Data Index: 1253347 (The Pile)

Max Activating Token Index: 517

Text #13

Max Range: 0.8217. Min Range: -0.8217

Max Act: 0.5549. Min Act: -0.0000

Data Index: 974046 (The Pile)

Max Activating Token Index: 63

Text #14

Max Range: 0.8217. Min Range: -0.8217

Max Act: 0.5577. Min Act: -0.0000

Data Index: 1378453 (The Pile)

Max Activating Token Index: 807

Text #15

Max Range: 0.8217. Min Range: -0.8217

Max Act: 0.5399. Min Act: -0.0000

Data Index: 1690084 (The Pile)

Max Activating Token Index: 996

Text #16

Max Range: 0.8217. Min Range: -0.8217

Max Act: 0.5109. Min Act: -0.0000

Data Index: 510864 (The Pile)

Max Activating Token Index: 311

Text #17

Max Range: 0.8217. Min Range: -0.8217

Max Act: 0.4773. Min Act: -0.0000

Data Index: 1001143 (The Pile)

Max Activating Token Index: 234

Text #18

Max Range: 0.8217. Min Range: -0.8217

Max Act: 0.6489. Min Act: -0.0000

Data Index: 1509108 (The Pile)

Max Activating Token Index: 428

Text #19

Max Range: 0.8217. Min Range: -0.8217

Max Act: 0.5139. Min Act: -0.0000

Data Index: 1308631 (The Pile)

Max Activating Token Index: 703