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

Dataset: The Pile

Neuron 1768 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: 0.5261. Min Range: -0.5261

Max Act: 0.4991. Min Act: -0.0000

Data Index: 1555070 (The Pile)

Max Activating Token Index: 385

Text #1

Max Range: 0.5261. Min Range: -0.5261

Max Act: 0.4802. Min Act: -0.0000

Data Index: 91500 (The Pile)

Max Activating Token Index: 456

Text #2

Max Range: 0.5261. Min Range: -0.5261

Max Act: 0.5261. Min Act: -0.0000

Data Index: 1356170 (The Pile)

Max Activating Token Index: 759

Text #3

Max Range: 0.5261. Min Range: -0.5261

Max Act: 0.5108. Min Act: -0.0000

Data Index: 973903 (The Pile)

Max Activating Token Index: 756

Text #4

Max Range: 0.5261. Min Range: -0.5261

Max Act: 0.4048. Min Act: -0.0000

Data Index: 865657 (The Pile)

Max Activating Token Index: 418

Text #5

Max Range: 0.5261. Min Range: -0.5261

Max Act: 0.4321. Min Act: -0.0000

Data Index: 524122 (The Pile)

Max Activating Token Index: 574

Text #6

Max Range: 0.5261. Min Range: -0.5261

Max Act: 0.4362. Min Act: -0.0000

Data Index: 1464192 (The Pile)

Max Activating Token Index: 488

Text #7

Max Range: 0.5261. Min Range: -0.5261

Max Act: 0.4501. Min Act: -0.0000

Data Index: 80083 (The Pile)

Max Activating Token Index: 551

Text #8

Max Range: 0.5261. Min Range: -0.5261

Max Act: 0.4668. Min Act: -0.0000

Data Index: 1410492 (The Pile)

Max Activating Token Index: 952

Text #9

Max Range: 0.5261. Min Range: -0.5261

Max Act: 0.3894. Min Act: -0.0000

Data Index: 1198024 (The Pile)

Max Activating Token Index: 775

Text #10

Max Range: 0.5261. Min Range: -0.5261

Max Act: 0.3954. Min Act: -0.0000

Data Index: 426578 (The Pile)

Max Activating Token Index: 463

Text #11

Max Range: 0.5261. Min Range: -0.5261

Max Act: 0.4077. Min Act: -0.0000

Data Index: 764695 (The Pile)

Max Activating Token Index: 469

Text #12

Max Range: 0.5261. Min Range: -0.5261

Max Act: 0.4200. Min Act: -0.0000

Data Index: 500976 (The Pile)

Max Activating Token Index: 723

Text #13

Max Range: 0.5261. Min Range: -0.5261

Max Act: 0.4454. Min Act: -0.0000

Data Index: 327820 (The Pile)

Max Activating Token Index: 733

Text #14

Max Range: 0.5261. Min Range: -0.5261

Max Act: 0.4284. Min Act: -0.0000

Data Index: 627251 (The Pile)

Max Activating Token Index: 534

Text #15

Max Range: 0.5261. Min Range: -0.5261

Max Act: 0.3838. Min Act: -0.0000

Data Index: 1677980 (The Pile)

Max Activating Token Index: 536

Text #16

Max Range: 0.5261. Min Range: -0.5261

Max Act: 0.4083. Min Act: -0.0000

Data Index: 1468655 (The Pile)

Max Activating Token Index: 448

Text #17

Max Range: 0.5261. Min Range: -0.5261

Max Act: 0.4742. Min Act: -0.0000

Data Index: 277793 (The Pile)

Max Activating Token Index: 525

Text #18

Max Range: 0.5261. Min Range: -0.5261

Max Act: 0.4231. Min Act: -0.0000

Data Index: 592769 (The Pile)

Max Activating Token Index: 597

Text #19

Max Range: 0.5261. Min Range: -0.5261

Max Act: 0.4292. Min Act: -0.0000

Data Index: 1058665 (The Pile)

Max Activating Token Index: 578