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

Dataset: The Pile

Neuron 798 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1064. Min Range: -1.1064

Max Act: 1.1064. Min Act: -0.0000

Data Index: 491422 (The Pile)

Max Activating Token Index: 838

Text #1

Max Range: 1.1064. Min Range: -1.1064

Max Act: 0.9472. Min Act: -0.0000

Data Index: 45392 (The Pile)

Max Activating Token Index: 1009

Text #2

Max Range: 1.1064. Min Range: -1.1064

Max Act: 0.9343. Min Act: -0.0000

Data Index: 1031514 (The Pile)

Max Activating Token Index: 178

Text #3

Max Range: 1.1064. Min Range: -1.1064

Max Act: 0.8321. Min Act: -0.0000

Data Index: 275604 (The Pile)

Max Activating Token Index: 625

Text #4

Max Range: 1.1064. Min Range: -1.1064

Max Act: 0.8668. Min Act: -0.0000

Data Index: 1800186 (The Pile)

Max Activating Token Index: 734

Text #5

Max Range: 1.1064. Min Range: -1.1064

Max Act: 0.8338. Min Act: -0.0000

Data Index: 192471 (The Pile)

Max Activating Token Index: 383

Text #6

Max Range: 1.1064. Min Range: -1.1064

Max Act: 0.8261. Min Act: -0.0000

Data Index: 471457 (The Pile)

Max Activating Token Index: 588

Text #7

Max Range: 1.1064. Min Range: -1.1064

Max Act: 0.7722. Min Act: -0.0000

Data Index: 772604 (The Pile)

Max Activating Token Index: 465

Text #8

Max Range: 1.1064. Min Range: -1.1064

Max Act: 0.7793. Min Act: -0.0000

Data Index: 667710 (The Pile)

Max Activating Token Index: 161

Text #9

Max Range: 1.1064. Min Range: -1.1064

Max Act: 0.8059. Min Act: -0.0000

Data Index: 421374 (The Pile)

Max Activating Token Index: 138

Text #10

Max Range: 1.1064. Min Range: -1.1064

Max Act: 0.7751. Min Act: -0.0000

Data Index: 254865 (The Pile)

Max Activating Token Index: 386

Text #11

Max Range: 1.1064. Min Range: -1.1064

Max Act: 0.7981. Min Act: -0.0000

Data Index: 612842 (The Pile)

Max Activating Token Index: 702

Text #12

Max Range: 1.1064. Min Range: -1.1064

Max Act: 0.7717. Min Act: -0.0000

Data Index: 680284 (The Pile)

Max Activating Token Index: 494

Text #13

Max Range: 1.1064. Min Range: -1.1064

Max Act: 0.7425. Min Act: -0.0000

Data Index: 1505699 (The Pile)

Max Activating Token Index: 593

Text #14

Max Range: 1.1064. Min Range: -1.1064

Max Act: 0.7929. Min Act: -0.0000

Data Index: 1484684 (The Pile)

Max Activating Token Index: 690

Text #15

Max Range: 1.1064. Min Range: -1.1064

Max Act: 0.7944. Min Act: -0.0000

Data Index: 1757600 (The Pile)

Max Activating Token Index: 493

Text #16

Max Range: 1.1064. Min Range: -1.1064

Max Act: 0.7611. Min Act: -0.0000

Data Index: 411561 (The Pile)

Max Activating Token Index: 85

Text #17

Max Range: 1.1064. Min Range: -1.1064

Max Act: 0.7519. Min Act: -0.0000

Data Index: 1757415 (The Pile)

Max Activating Token Index: 512

Text #18

Max Range: 1.1064. Min Range: -1.1064

Max Act: 0.7812. Min Act: -0.0000

Data Index: 607532 (The Pile)

Max Activating Token Index: 67

Text #19

Max Range: 1.1064. Min Range: -1.1064

Max Act: 0.7945. Min Act: -0.0000

Data Index: 8807 (The Pile)

Max Activating Token Index: 692