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

Dataset: The Pile

Neuron 4738 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.5429. Min Range: -5.5429

Max Act: 5.5429. Min Act: -0.0000

Data Index: 33171 (The Pile)

Max Activating Token Index: 1010

Text #1

Max Range: 5.5429. Min Range: -5.5429

Max Act: 4.5543. Min Act: -0.0000

Data Index: 1389570 (The Pile)

Max Activating Token Index: 138

Text #2

Max Range: 5.5429. Min Range: -5.5429

Max Act: 4.3693. Min Act: -0.0000

Data Index: 599068 (The Pile)

Max Activating Token Index: 993

Text #3

Max Range: 5.5429. Min Range: -5.5429

Max Act: 4.4396. Min Act: -0.0000

Data Index: 1044696 (The Pile)

Max Activating Token Index: 242

Text #4

Max Range: 5.5429. Min Range: -5.5429

Max Act: 4.2167. Min Act: -0.0000

Data Index: 1183793 (The Pile)

Max Activating Token Index: 314

Text #5

Max Range: 5.5429. Min Range: -5.5429

Max Act: 4.1663. Min Act: -0.0000

Data Index: 1797962 (The Pile)

Max Activating Token Index: 898

Text #6

Max Range: 5.5429. Min Range: -5.5429

Max Act: 3.9370. Min Act: -0.0000

Data Index: 469488 (The Pile)

Max Activating Token Index: 802

Text #7

Max Range: 5.5429. Min Range: -5.5429

Max Act: 4.2700. Min Act: -0.0000

Data Index: 175488 (The Pile)

Max Activating Token Index: 834

Text #8

Max Range: 5.5429. Min Range: -5.5429

Max Act: 4.1997. Min Act: -0.0000

Data Index: 897975 (The Pile)

Max Activating Token Index: 719

Text #9

Max Range: 5.5429. Min Range: -5.5429

Max Act: 3.7646. Min Act: -0.0000

Data Index: 1512829 (The Pile)

Max Activating Token Index: 153

Text #10

Max Range: 5.5429. Min Range: -5.5429

Max Act: 3.7663. Min Act: -0.0000

Data Index: 14588 (The Pile)

Max Activating Token Index: 668

Text #11

Max Range: 5.5429. Min Range: -5.5429

Max Act: 3.3981. Min Act: -0.0000

Data Index: 24770 (The Pile)

Max Activating Token Index: 942

Text #12

Max Range: 5.5429. Min Range: -5.5429

Max Act: 3.7293. Min Act: -0.0000

Data Index: 272894 (The Pile)

Max Activating Token Index: 101

Text #13

Max Range: 5.5429. Min Range: -5.5429

Max Act: 3.7030. Min Act: -0.0000

Data Index: 1672299 (The Pile)

Max Activating Token Index: 166

Text #14

Max Range: 5.5429. Min Range: -5.5429

Max Act: 3.7006. Min Act: -0.0000

Data Index: 1058250 (The Pile)

Max Activating Token Index: 967

Text #15

Max Range: 5.5429. Min Range: -5.5429

Max Act: 3.8283. Min Act: -0.0000

Data Index: 440926 (The Pile)

Max Activating Token Index: 415

Text #16

Max Range: 5.5429. Min Range: -5.5429

Max Act: 3.6436. Min Act: -0.0000

Data Index: 16693 (The Pile)

Max Activating Token Index: 112

Text #17

Max Range: 5.5429. Min Range: -5.5429

Max Act: 3.7057. Min Act: -0.0000

Data Index: 1559361 (The Pile)

Max Activating Token Index: 635

Text #18

Max Range: 5.5429. Min Range: -5.5429

Max Act: 3.5401. Min Act: -0.0000

Data Index: 261793 (The Pile)

Max Activating Token Index: 184

Text #19

Max Range: 5.5429. Min Range: -5.5429

Max Act: 3.8383. Min Act: -0.0000

Data Index: 1970344 (The Pile)

Max Activating Token Index: 869