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

Dataset: The Pile

Neuron 1976 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6755. Min Range: -0.6755

Max Act: 0.6755. Min Act: -0.0000

Data Index: 508776 (The Pile)

Max Activating Token Index: 878

Text #1

Max Range: 0.6755. Min Range: -0.6755

Max Act: 0.6383. Min Act: -0.0000

Data Index: 47274 (The Pile)

Max Activating Token Index: 994

Text #2

Max Range: 0.6755. Min Range: -0.6755

Max Act: 0.6722. Min Act: 0.0000

Data Index: 1282017 (The Pile)

Max Activating Token Index: 613

Text #3

Max Range: 0.6755. Min Range: -0.6755

Max Act: 0.6113. Min Act: -0.0000

Data Index: 275852 (The Pile)

Max Activating Token Index: 785

Text #4

Max Range: 0.6755. Min Range: -0.6755

Max Act: 0.5386. Min Act: -0.0000

Data Index: 1396794 (The Pile)

Max Activating Token Index: 786

Text #5

Max Range: 0.6755. Min Range: -0.6755

Max Act: 0.6015. Min Act: -0.0000

Data Index: 219773 (The Pile)

Max Activating Token Index: 921

Text #6

Max Range: 0.6755. Min Range: -0.6755

Max Act: 0.6061. Min Act: -0.0000

Data Index: 883769 (The Pile)

Max Activating Token Index: 734

Text #7

Max Range: 0.6755. Min Range: -0.6755

Max Act: 0.6113. Min Act: -0.0000

Data Index: 706011 (The Pile)

Max Activating Token Index: 682

Text #8

Max Range: 0.6755. Min Range: -0.6755

Max Act: 0.5663. Min Act: -0.0000

Data Index: 76776 (The Pile)

Max Activating Token Index: 1005

Text #9

Max Range: 0.6755. Min Range: -0.6755

Max Act: 0.5228. Min Act: -0.0000

Data Index: 1565215 (The Pile)

Max Activating Token Index: 922

Text #10

Max Range: 0.6755. Min Range: -0.6755

Max Act: 0.5672. Min Act: -0.0000

Data Index: 415944 (The Pile)

Max Activating Token Index: 647

Text #11

Max Range: 0.6755. Min Range: -0.6755

Max Act: 0.5061. Min Act: -0.0000

Data Index: 427063 (The Pile)

Max Activating Token Index: 587

Text #12

Max Range: 0.6755. Min Range: -0.6755

Max Act: 0.4982. Min Act: -0.0000

Data Index: 748966 (The Pile)

Max Activating Token Index: 633

Text #13

Max Range: 0.6755. Min Range: -0.6755

Max Act: 0.5646. Min Act: -0.0000

Data Index: 136406 (The Pile)

Max Activating Token Index: 1015

Text #14

Max Range: 0.6755. Min Range: -0.6755

Max Act: 0.4374. Min Act: -0.0000

Data Index: 845262 (The Pile)

Max Activating Token Index: 962

Text #15

Max Range: 0.6755. Min Range: -0.6755

Max Act: 0.4833. Min Act: -0.0000

Data Index: 1901976 (The Pile)

Max Activating Token Index: 1004

Text #16

Max Range: 0.6755. Min Range: -0.6755

Max Act: 0.4653. Min Act: -0.0000

Data Index: 1553502 (The Pile)

Max Activating Token Index: 559

Text #17

Max Range: 0.6755. Min Range: -0.6755

Max Act: 0.5134. Min Act: -0.0000

Data Index: 1868078 (The Pile)

Max Activating Token Index: 175

Text #18

Max Range: 0.6755. Min Range: -0.6755

Max Act: 0.4388. Min Act: -0.0000

Data Index: 1532180 (The Pile)

Max Activating Token Index: 733

Text #19

Max Range: 0.6755. Min Range: -0.6755

Max Act: 0.4326. Min Act: -0.0000

Data Index: 556081 (The Pile)

Max Activating Token Index: 577