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

Dataset: The Pile

Neuron 4757 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3839. Min Range: -0.3839

Max Act: 0.3535. Min Act: -0.0000

Data Index: 1094638 (The Pile)

Max Activating Token Index: 858

Text #1

Max Range: 0.3839. Min Range: -0.3839

Max Act: 0.3839. Min Act: -0.0000

Data Index: 972563 (The Pile)

Max Activating Token Index: 1019

Text #2

Max Range: 0.3839. Min Range: -0.3839

Max Act: 0.3510. Min Act: -0.0000

Data Index: 1570525 (The Pile)

Max Activating Token Index: 288

Text #3

Max Range: 0.3839. Min Range: -0.3839

Max Act: 0.3699. Min Act: -0.0000

Data Index: 494918 (The Pile)

Max Activating Token Index: 97

Text #4

Max Range: 0.3839. Min Range: -0.3839

Max Act: 0.3507. Min Act: -0.0000

Data Index: 1004875 (The Pile)

Max Activating Token Index: 46

Text #5

Max Range: 0.3839. Min Range: -0.3839

Max Act: 0.3598. Min Act: -0.0000

Data Index: 1673758 (The Pile)

Max Activating Token Index: 701

Text #6

Max Range: 0.3839. Min Range: -0.3839

Max Act: 0.3711. Min Act: -0.0000

Data Index: 1123619 (The Pile)

Max Activating Token Index: 276

Text #7

Max Range: 0.3839. Min Range: -0.3839

Max Act: 0.3468. Min Act: -0.0000

Data Index: 441811 (The Pile)

Max Activating Token Index: 914

Text #8

Max Range: 0.3839. Min Range: -0.3839

Max Act: 0.3450. Min Act: -0.0000

Data Index: 1355679 (The Pile)

Max Activating Token Index: 545

Text #9

Max Range: 0.3839. Min Range: -0.3839

Max Act: 0.3502. Min Act: -0.0000

Data Index: 1901322 (The Pile)

Max Activating Token Index: 386

Text #10

Max Range: 0.3839. Min Range: -0.3839

Max Act: 0.3543. Min Act: -0.0000

Data Index: 1596412 (The Pile)

Max Activating Token Index: 441

Text #11

Max Range: 0.3839. Min Range: -0.3839

Max Act: 0.3173. Min Act: -0.0000

Data Index: 1182186 (The Pile)

Max Activating Token Index: 789

Text #12

Max Range: 0.3839. Min Range: -0.3839

Max Act: 0.3593. Min Act: -0.0000

Data Index: 1324230 (The Pile)

Max Activating Token Index: 994

Text #13

Max Range: 0.3839. Min Range: -0.3839

Max Act: 0.3434. Min Act: -0.0000

Data Index: 134946 (The Pile)

Max Activating Token Index: 161

Text #14

Max Range: 0.3839. Min Range: -0.3839

Max Act: 0.3558. Min Act: -0.0000

Data Index: 831470 (The Pile)

Max Activating Token Index: 596

Text #15

Max Range: 0.3839. Min Range: -0.3839

Max Act: 0.3543. Min Act: -0.0000

Data Index: 208318 (The Pile)

Max Activating Token Index: 640

Text #16

Max Range: 0.3839. Min Range: -0.3839

Max Act: 0.3260. Min Act: -0.0000

Data Index: 1460004 (The Pile)

Max Activating Token Index: 110

Text #17

Max Range: 0.3839. Min Range: -0.3839

Max Act: 0.2997. Min Act: -0.0000

Data Index: 739044 (The Pile)

Max Activating Token Index: 841

Text #18

Max Range: 0.3839. Min Range: -0.3839

Max Act: 0.3700. Min Act: -0.0000

Data Index: 223724 (The Pile)

Max Activating Token Index: 839

Text #19

Max Range: 0.3839. Min Range: -0.3839

Max Act: 0.3126. Min Act: -0.0000

Data Index: 371886 (The Pile)

Max Activating Token Index: 730