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

Dataset: The Pile

Neuron 4013 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6940. Min Range: -0.6940

Max Act: 0.6940. Min Act: -0.0000

Data Index: 1191535 (The Pile)

Max Activating Token Index: 370

Text #1

Max Range: 0.6940. Min Range: -0.6940

Max Act: 0.6196. Min Act: -0.0000

Data Index: 441521 (The Pile)

Max Activating Token Index: 969

Text #2

Max Range: 0.6940. Min Range: -0.6940

Max Act: 0.6333. Min Act: -0.0000

Data Index: 402602 (The Pile)

Max Activating Token Index: 604

Text #3

Max Range: 0.6940. Min Range: -0.6940

Max Act: 0.6505. Min Act: -0.0000

Data Index: 882328 (The Pile)

Max Activating Token Index: 1020

Text #4

Max Range: 0.6940. Min Range: -0.6940

Max Act: 0.6407. Min Act: -0.0000

Data Index: 1731385 (The Pile)

Max Activating Token Index: 190

Text #5

Max Range: 0.6940. Min Range: -0.6940

Max Act: 0.6010. Min Act: -0.0000

Data Index: 1758382 (The Pile)

Max Activating Token Index: 226

Text #6

Max Range: 0.6940. Min Range: -0.6940

Max Act: 0.6150. Min Act: -0.0000

Data Index: 928379 (The Pile)

Max Activating Token Index: 850

Text #7

Max Range: 0.6940. Min Range: -0.6940

Max Act: 0.5958. Min Act: -0.0000

Data Index: 1596344 (The Pile)

Max Activating Token Index: 823

Text #8

Max Range: 0.6940. Min Range: -0.6940

Max Act: 0.6103. Min Act: -0.0000

Data Index: 434153 (The Pile)

Max Activating Token Index: 156

Text #9

Max Range: 0.6940. Min Range: -0.6940

Max Act: 0.6082. Min Act: -0.0000

Data Index: 1722216 (The Pile)

Max Activating Token Index: 852

Text #10

Max Range: 0.6940. Min Range: -0.6940

Max Act: 0.6081. Min Act: -0.0000

Data Index: 574836 (The Pile)

Max Activating Token Index: 349

Text #11

Max Range: 0.6940. Min Range: -0.6940

Max Act: 0.6249. Min Act: -0.0000

Data Index: 751016 (The Pile)

Max Activating Token Index: 327

Text #12

Max Range: 0.6940. Min Range: -0.6940

Max Act: 0.5811. Min Act: -0.0000

Data Index: 372373 (The Pile)

Max Activating Token Index: 804

Text #13

Max Range: 0.6940. Min Range: -0.6940

Max Act: 0.5875. Min Act: -0.0000

Data Index: 343527 (The Pile)

Max Activating Token Index: 632

Text #14

Max Range: 0.6940. Min Range: -0.6940

Max Act: 0.6054. Min Act: -0.0000

Data Index: 993052 (The Pile)

Max Activating Token Index: 167

Text #15

Max Range: 0.6940. Min Range: -0.6940

Max Act: 0.5596. Min Act: -0.0000

Data Index: 1924275 (The Pile)

Max Activating Token Index: 999

Text #16

Max Range: 0.6940. Min Range: -0.6940

Max Act: 0.5455. Min Act: -0.0000

Data Index: 1807132 (The Pile)

Max Activating Token Index: 57

Text #17

Max Range: 0.6940. Min Range: -0.6940

Max Act: 0.5797. Min Act: -0.0000

Data Index: 1009107 (The Pile)

Max Activating Token Index: 528

Text #18

Max Range: 0.6940. Min Range: -0.6940

Max Act: 0.5827. Min Act: -0.0000

Data Index: 1542139 (The Pile)

Max Activating Token Index: 739

Text #19

Max Range: 0.6940. Min Range: -0.6940

Max Act: 0.5954. Min Act: -0.0000

Data Index: 453343 (The Pile)

Max Activating Token Index: 916