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

Dataset: The Pile

Neuron 4532 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6366. Min Range: -0.6366

Max Act: 0.6366. Min Act: -0.0000

Data Index: 1938121 (The Pile)

Max Activating Token Index: 977

Text #1

Max Range: 0.6366. Min Range: -0.6366

Max Act: 0.5648. Min Act: -0.0000

Data Index: 1872024 (The Pile)

Max Activating Token Index: 596

Text #2

Max Range: 0.6366. Min Range: -0.6366

Max Act: 0.4363. Min Act: -0.0000

Data Index: 1850932 (The Pile)

Max Activating Token Index: 118

Text #3

Max Range: 0.6366. Min Range: -0.6366

Max Act: 0.3954. Min Act: -0.0000

Data Index: 1264680 (The Pile)

Max Activating Token Index: 236

Text #4

Max Range: 0.6366. Min Range: -0.6366

Max Act: 0.3931. Min Act: -0.0000

Data Index: 1484782 (The Pile)

Max Activating Token Index: 422

Text #5

Max Range: 0.6366. Min Range: -0.6366

Max Act: 0.3925. Min Act: -0.0000

Data Index: 1507815 (The Pile)

Max Activating Token Index: 694

Text #6

Max Range: 0.6366. Min Range: -0.6366

Max Act: 0.3896. Min Act: -0.0000

Data Index: 436406 (The Pile)

Max Activating Token Index: 324

Text #7

Max Range: 0.6366. Min Range: -0.6366

Max Act: 0.4046. Min Act: -0.0000

Data Index: 988671 (The Pile)

Max Activating Token Index: 430

Text #8

Max Range: 0.6366. Min Range: -0.6366

Max Act: 0.3838. Min Act: -0.0000

Data Index: 1649607 (The Pile)

Max Activating Token Index: 1000

Text #9

Max Range: 0.6366. Min Range: -0.6366

Max Act: 0.3846. Min Act: -0.0000

Data Index: 52183 (The Pile)

Max Activating Token Index: 537

Text #10

Max Range: 0.6366. Min Range: -0.6366

Max Act: 0.3709. Min Act: -0.0000

Data Index: 1898259 (The Pile)

Max Activating Token Index: 743

Text #11

Max Range: 0.6366. Min Range: -0.6366

Max Act: 0.3479. Min Act: -0.0000

Data Index: 786962 (The Pile)

Max Activating Token Index: 1014

Text #12

Max Range: 0.6366. Min Range: -0.6366

Max Act: 0.3739. Min Act: -0.0000

Data Index: 859407 (The Pile)

Max Activating Token Index: 806

Text #13

Max Range: 0.6366. Min Range: -0.6366

Max Act: 0.3526. Min Act: -0.0000

Data Index: 1117505 (The Pile)

Max Activating Token Index: 334

Text #14

Max Range: 0.6366. Min Range: -0.6366

Max Act: 0.3600. Min Act: -0.0000

Data Index: 1450266 (The Pile)

Max Activating Token Index: 518

Text #15

Max Range: 0.6366. Min Range: -0.6366

Max Act: 0.3739. Min Act: -0.0000

Data Index: 1510307 (The Pile)

Max Activating Token Index: 530

Text #16

Max Range: 0.6366. Min Range: -0.6366

Max Act: 0.3458. Min Act: -0.0000

Data Index: 1976414 (The Pile)

Max Activating Token Index: 618

Text #17

Max Range: 0.6366. Min Range: -0.6366

Max Act: 0.3560. Min Act: -0.0000

Data Index: 649312 (The Pile)

Max Activating Token Index: 645

Text #18

Max Range: 0.6366. Min Range: -0.6366

Max Act: 0.3654. Min Act: -0.0000

Data Index: 867892 (The Pile)

Max Activating Token Index: 444

Text #19

Max Range: 0.6366. Min Range: -0.6366

Max Act: 0.3425. Min Act: -0.0000

Data Index: 1078734 (The Pile)

Max Activating Token Index: 512