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

Dataset: The Pile

Neuron 3925 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: 5.2597. Min Range: -5.2597

Max Act: 5.2597. Min Act: -0.0000

Data Index: 120529 (The Pile)

Max Activating Token Index: 352

Text #1

Max Range: 5.2597. Min Range: -5.2597

Max Act: 5.0875. Min Act: -0.0000

Data Index: 259336 (The Pile)

Max Activating Token Index: 294

Text #2

Max Range: 5.2597. Min Range: -5.2597

Max Act: 4.3961. Min Act: -0.0000

Data Index: 502197 (The Pile)

Max Activating Token Index: 110

Text #3

Max Range: 5.2597. Min Range: -5.2597

Max Act: 3.9399. Min Act: -0.0000

Data Index: 1985250 (The Pile)

Max Activating Token Index: 753

Text #4

Max Range: 5.2597. Min Range: -5.2597

Max Act: 4.4397. Min Act: -0.0000

Data Index: 838945 (The Pile)

Max Activating Token Index: 377

Text #5

Max Range: 5.2597. Min Range: -5.2597

Max Act: 4.2004. Min Act: -0.0000

Data Index: 147340 (The Pile)

Max Activating Token Index: 25

Text #6

Max Range: 5.2597. Min Range: -5.2597

Max Act: 4.3551. Min Act: -0.0000

Data Index: 16283 (The Pile)

Max Activating Token Index: 44

Text #7

Max Range: 5.2597. Min Range: -5.2597

Max Act: 4.4126. Min Act: -0.0000

Data Index: 1564348 (The Pile)

Max Activating Token Index: 798

Text #8

Max Range: 5.2597. Min Range: -5.2597

Max Act: 4.2491. Min Act: -0.0000

Data Index: 1903823 (The Pile)

Max Activating Token Index: 247

Text #9

Max Range: 5.2597. Min Range: -5.2597

Max Act: 4.0588. Min Act: -0.0000

Data Index: 40013 (The Pile)

Max Activating Token Index: 462

Text #10

Max Range: 5.2597. Min Range: -5.2597

Max Act: 4.2022. Min Act: -0.0000

Data Index: 967514 (The Pile)

Max Activating Token Index: 100

Text #11

Max Range: 5.2597. Min Range: -5.2597

Max Act: 3.9809. Min Act: -0.0000

Data Index: 1394138 (The Pile)

Max Activating Token Index: 73

Text #12

Max Range: 5.2597. Min Range: -5.2597

Max Act: 3.9668. Min Act: -0.0000

Data Index: 1801643 (The Pile)

Max Activating Token Index: 191

Text #13

Max Range: 5.2597. Min Range: -5.2597

Max Act: 4.4682. Min Act: -0.0000

Data Index: 1760811 (The Pile)

Max Activating Token Index: 165

Text #14

Max Range: 5.2597. Min Range: -5.2597

Max Act: 4.2713. Min Act: -0.0000

Data Index: 785600 (The Pile)

Max Activating Token Index: 716

Text #15

Max Range: 5.2597. Min Range: -5.2597

Max Act: 4.0686. Min Act: -0.0000

Data Index: 1962254 (The Pile)

Max Activating Token Index: 235

Text #16

Max Range: 5.2597. Min Range: -5.2597

Max Act: 4.0529. Min Act: -0.0000

Data Index: 20461 (The Pile)

Max Activating Token Index: 67

Text #17

Max Range: 5.2597. Min Range: -5.2597

Max Act: 4.0925. Min Act: -0.0000

Data Index: 1925982 (The Pile)

Max Activating Token Index: 83

Text #18

Max Range: 5.2597. Min Range: -5.2597

Max Act: 3.8718. Min Act: -0.0000

Data Index: 698086 (The Pile)

Max Activating Token Index: 360

Text #19

Max Range: 5.2597. Min Range: -5.2597

Max Act: 4.1765. Min Act: -0.0000

Data Index: 876573 (The Pile)

Max Activating Token Index: 322