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

Dataset: The Pile

Neuron 1547 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: 1.9577. Min Range: -1.9577

Max Act: 1.9577. Min Act: -0.0000

Data Index: 1282464 (The Pile)

Max Activating Token Index: 950

Text #1

Max Range: 1.9577. Min Range: -1.9577

Max Act: 1.8985. Min Act: -0.0000

Data Index: 1236867 (The Pile)

Max Activating Token Index: 780

Text #2

Max Range: 1.9577. Min Range: -1.9577

Max Act: 1.6459. Min Act: -0.0000

Data Index: 1468778 (The Pile)

Max Activating Token Index: 548

Text #3

Max Range: 1.9577. Min Range: -1.9577

Max Act: 1.7056. Min Act: -0.0000

Data Index: 145094 (The Pile)

Max Activating Token Index: 555

Text #4

Max Range: 1.9577. Min Range: -1.9577

Max Act: 1.5484. Min Act: -0.0000

Data Index: 869503 (The Pile)

Max Activating Token Index: 789

Text #5

Max Range: 1.9577. Min Range: -1.9577

Max Act: 1.6139. Min Act: -0.0000

Data Index: 363878 (The Pile)

Max Activating Token Index: 167

Text #6

Max Range: 1.9577. Min Range: -1.9577

Max Act: 1.4106. Min Act: -0.0000

Data Index: 82553 (The Pile)

Max Activating Token Index: 488

Text #7

Max Range: 1.9577. Min Range: -1.9577

Max Act: 1.4600. Min Act: -0.0000

Data Index: 915463 (The Pile)

Max Activating Token Index: 557

Text #8

Max Range: 1.9577. Min Range: -1.9577

Max Act: 1.4452. Min Act: -0.0000

Data Index: 995760 (The Pile)

Max Activating Token Index: 162

Text #9

Max Range: 1.9577. Min Range: -1.9577

Max Act: 1.4477. Min Act: -0.0000

Data Index: 31232 (The Pile)

Max Activating Token Index: 507

Text #10

Max Range: 1.9577. Min Range: -1.9577

Max Act: 1.2835. Min Act: -0.0000

Data Index: 1597165 (The Pile)

Max Activating Token Index: 730

Text #11

Max Range: 1.9577. Min Range: -1.9577

Max Act: 1.4074. Min Act: -0.0000

Data Index: 1350357 (The Pile)

Max Activating Token Index: 1019

Text #12

Max Range: 1.9577. Min Range: -1.9577

Max Act: 1.4723. Min Act: -0.0000

Data Index: 1723731 (The Pile)

Max Activating Token Index: 430

Text #13

Max Range: 1.9577. Min Range: -1.9577

Max Act: 1.3005. Min Act: -0.0000

Data Index: 105714 (The Pile)

Max Activating Token Index: 949

Text #14

Max Range: 1.9577. Min Range: -1.9577

Max Act: 1.4529. Min Act: -0.0000

Data Index: 967264 (The Pile)

Max Activating Token Index: 832

Text #15

Max Range: 1.9577. Min Range: -1.9577

Max Act: 1.2900. Min Act: -0.0000

Data Index: 639561 (The Pile)

Max Activating Token Index: 101

Text #16

Max Range: 1.9577. Min Range: -1.9577

Max Act: 1.3621. Min Act: -0.0000

Data Index: 754543 (The Pile)

Max Activating Token Index: 961

Text #17

Max Range: 1.9577. Min Range: -1.9577

Max Act: 1.3584. Min Act: -0.0000

Data Index: 841706 (The Pile)

Max Activating Token Index: 370

Text #18

Max Range: 1.9577. Min Range: -1.9577

Max Act: 1.3497. Min Act: -0.0000

Data Index: 1476053 (The Pile)

Max Activating Token Index: 775

Text #19

Max Range: 1.9577. Min Range: -1.9577

Max Act: 1.3337. Min Act: -0.0000

Data Index: 854376 (The Pile)

Max Activating Token Index: 384