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

Dataset: The Pile

Neuron 336 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.6915. Min Range: -0.6915

Max Act: 0.6915. Min Act: -0.0000

Data Index: 491872 (The Pile)

Max Activating Token Index: 610

Text #1

Max Range: 0.6915. Min Range: -0.6915

Max Act: 0.6468. Min Act: -0.0000

Data Index: 252901 (The Pile)

Max Activating Token Index: 383

Text #2

Max Range: 0.6915. Min Range: -0.6915

Max Act: 0.6574. Min Act: -0.0000

Data Index: 1374191 (The Pile)

Max Activating Token Index: 771

Text #3

Max Range: 0.6915. Min Range: -0.6915

Max Act: 0.6712. Min Act: 0.0000

Data Index: 631267 (The Pile)

Max Activating Token Index: 143

Text #4

Max Range: 0.6915. Min Range: -0.6915

Max Act: 0.6740. Min Act: -0.0000

Data Index: 973582 (The Pile)

Max Activating Token Index: 984

Text #5

Max Range: 0.6915. Min Range: -0.6915

Max Act: 0.6601. Min Act: -0.0000

Data Index: 29864 (The Pile)

Max Activating Token Index: 861

Text #6

Max Range: 0.6915. Min Range: -0.6915

Max Act: 0.6431. Min Act: -0.0000

Data Index: 770267 (The Pile)

Max Activating Token Index: 409

Text #7

Max Range: 0.6915. Min Range: -0.6915

Max Act: 0.6516. Min Act: -0.0000

Data Index: 818993 (The Pile)

Max Activating Token Index: 381

Text #8

Max Range: 0.6915. Min Range: -0.6915

Max Act: 0.6495. Min Act: -0.0000

Data Index: 330417 (The Pile)

Max Activating Token Index: 504

Text #9

Max Range: 0.6915. Min Range: -0.6915

Max Act: 0.6447. Min Act: -0.0000

Data Index: 1814873 (The Pile)

Max Activating Token Index: 819

Text #10

Max Range: 0.6915. Min Range: -0.6915

Max Act: 0.6696. Min Act: -0.0000

Data Index: 1180298 (The Pile)

Max Activating Token Index: 195

Text #11

Max Range: 0.6915. Min Range: -0.6915

Max Act: 0.6360. Min Act: -0.0000

Data Index: 1948806 (The Pile)

Max Activating Token Index: 213

Text #12

Max Range: 0.6915. Min Range: -0.6915

Max Act: 0.5947. Min Act: -0.0000

Data Index: 1893069 (The Pile)

Max Activating Token Index: 726

Text #13

Max Range: 0.6915. Min Range: -0.6915

Max Act: 0.6261. Min Act: 0.0000

Data Index: 1730982 (The Pile)

Max Activating Token Index: 202

Text #14

Max Range: 0.6915. Min Range: -0.6915

Max Act: 0.6413. Min Act: -0.0000

Data Index: 562132 (The Pile)

Max Activating Token Index: 730

Text #15

Max Range: 0.6915. Min Range: -0.6915

Max Act: 0.6137. Min Act: -0.0000

Data Index: 973073 (The Pile)

Max Activating Token Index: 777

Text #16

Max Range: 0.6915. Min Range: -0.6915

Max Act: 0.5925. Min Act: -0.0000

Data Index: 1502634 (The Pile)

Max Activating Token Index: 265

Text #17

Max Range: 0.6915. Min Range: -0.6915

Max Act: 0.5892. Min Act: -0.0000

Data Index: 1146096 (The Pile)

Max Activating Token Index: 79

Text #18

Max Range: 0.6915. Min Range: -0.6915

Max Act: 0.5817. Min Act: -0.0000

Data Index: 283673 (The Pile)

Max Activating Token Index: 856

Text #19

Max Range: 0.6915. Min Range: -0.6915

Max Act: 0.5799. Min Act: -0.0000

Data Index: 1899461 (The Pile)

Max Activating Token Index: 278