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

Dataset: The Pile

Neuron 3987 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: 1.5875. Min Range: -1.5875

Max Act: 1.5476. Min Act: -0.0000

Data Index: 925890 (The Pile)

Max Activating Token Index: 683

Text #1

Max Range: 1.5875. Min Range: -1.5875

Max Act: 1.4475. Min Act: -0.0000

Data Index: 136604 (The Pile)

Max Activating Token Index: 652

Text #2

Max Range: 1.5875. Min Range: -1.5875

Max Act: 1.5875. Min Act: -0.0000

Data Index: 58498 (The Pile)

Max Activating Token Index: 820

Text #3

Max Range: 1.5875. Min Range: -1.5875

Max Act: 1.3121. Min Act: -0.0000

Data Index: 1141842 (The Pile)

Max Activating Token Index: 384

Text #4

Max Range: 1.5875. Min Range: -1.5875

Max Act: 1.5793. Min Act: -0.0000

Data Index: 1136605 (The Pile)

Max Activating Token Index: 319

Text #5

Max Range: 1.5875. Min Range: -1.5875

Max Act: 1.1847. Min Act: -0.0000

Data Index: 378669 (The Pile)

Max Activating Token Index: 462

Text #6

Max Range: 1.5875. Min Range: -1.5875

Max Act: 1.4366. Min Act: -0.0000

Data Index: 1713403 (The Pile)

Max Activating Token Index: 773

Text #7

Max Range: 1.5875. Min Range: -1.5875

Max Act: 1.3051. Min Act: -0.0000

Data Index: 1732806 (The Pile)

Max Activating Token Index: 9

Text #8

Max Range: 1.5875. Min Range: -1.5875

Max Act: 1.4473. Min Act: -0.0000

Data Index: 645171 (The Pile)

Max Activating Token Index: 798

Text #9

Max Range: 1.5875. Min Range: -1.5875

Max Act: 1.4353. Min Act: -0.0000

Data Index: 464291 (The Pile)

Max Activating Token Index: 200

Text #10

Max Range: 1.5875. Min Range: -1.5875

Max Act: 1.1262. Min Act: -0.0000

Data Index: 1143934 (The Pile)

Max Activating Token Index: 699

Text #11

Max Range: 1.5875. Min Range: -1.5875

Max Act: 1.2699. Min Act: -0.0000

Data Index: 1993680 (The Pile)

Max Activating Token Index: 693

Text #12

Max Range: 1.5875. Min Range: -1.5875

Max Act: 1.2294. Min Act: -0.0000

Data Index: 839983 (The Pile)

Max Activating Token Index: 375

Text #13

Max Range: 1.5875. Min Range: -1.5875

Max Act: 1.0664. Min Act: -0.0000

Data Index: 844425 (The Pile)

Max Activating Token Index: 573

Text #14

Max Range: 1.5875. Min Range: -1.5875

Max Act: 1.2598. Min Act: -0.0000

Data Index: 1055412 (The Pile)

Max Activating Token Index: 20

Text #15

Max Range: 1.5875. Min Range: -1.5875

Max Act: 1.2062. Min Act: -0.0000

Data Index: 518873 (The Pile)

Max Activating Token Index: 324

Text #16

Max Range: 1.5875. Min Range: -1.5875

Max Act: 1.2669. Min Act: -0.0000

Data Index: 32237 (The Pile)

Max Activating Token Index: 8

Text #17

Max Range: 1.5875. Min Range: -1.5875

Max Act: 1.2316. Min Act: -0.0000

Data Index: 403304 (The Pile)

Max Activating Token Index: 105

Text #18

Max Range: 1.5875. Min Range: -1.5875

Max Act: 1.1340. Min Act: -0.0000

Data Index: 1703216 (The Pile)

Max Activating Token Index: 350

Text #19

Max Range: 1.5875. Min Range: -1.5875

Max Act: 1.2394. Min Act: -0.0000

Data Index: 124025 (The Pile)

Max Activating Token Index: 928