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

Dataset: The Pile

Neuron 1809 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.5353. Min Range: -4.5353

Max Act: 4.5353. Min Act: -0.0000

Data Index: 1810382 (The Pile)

Max Activating Token Index: 607

Text #1

Max Range: 4.5353. Min Range: -4.5353

Max Act: 4.0879. Min Act: -0.0000

Data Index: 1581666 (The Pile)

Max Activating Token Index: 826

Text #2

Max Range: 4.5353. Min Range: -4.5353

Max Act: 3.8792. Min Act: -0.0000

Data Index: 539126 (The Pile)

Max Activating Token Index: 30

Text #3

Max Range: 4.5353. Min Range: -4.5353

Max Act: 4.2522. Min Act: -0.0000

Data Index: 1860236 (The Pile)

Max Activating Token Index: 458

Text #4

Max Range: 4.5353. Min Range: -4.5353

Max Act: 4.2438. Min Act: -0.0000

Data Index: 517590 (The Pile)

Max Activating Token Index: 64

Text #5

Max Range: 4.5353. Min Range: -4.5353

Max Act: 3.9129. Min Act: -0.0000

Data Index: 194044 (The Pile)

Max Activating Token Index: 950

Text #6

Max Range: 4.5353. Min Range: -4.5353

Max Act: 4.0597. Min Act: -0.0000

Data Index: 1928992 (The Pile)

Max Activating Token Index: 1014

Text #7

Max Range: 4.5353. Min Range: -4.5353

Max Act: 4.0847. Min Act: -0.0000

Data Index: 1486981 (The Pile)

Max Activating Token Index: 412

Text #8

Max Range: 4.5353. Min Range: -4.5353

Max Act: 3.9825. Min Act: -0.0000

Data Index: 112707 (The Pile)

Max Activating Token Index: 855

Text #9

Max Range: 4.5353. Min Range: -4.5353

Max Act: 4.0168. Min Act: -0.0000

Data Index: 1292954 (The Pile)

Max Activating Token Index: 861

Text #10

Max Range: 4.5353. Min Range: -4.5353

Max Act: 3.9715. Min Act: -0.0000

Data Index: 765145 (The Pile)

Max Activating Token Index: 914

Text #11

Max Range: 4.5353. Min Range: -4.5353

Max Act: 3.9774. Min Act: 0.0000

Data Index: 110212 (The Pile)

Max Activating Token Index: 563

Text #12

Max Range: 4.5353. Min Range: -4.5353

Max Act: 3.9916. Min Act: -0.0000

Data Index: 457421 (The Pile)

Max Activating Token Index: 916

Text #13

Max Range: 4.5353. Min Range: -4.5353

Max Act: 3.8551. Min Act: -0.0000

Data Index: 873877 (The Pile)

Max Activating Token Index: 48

Text #14

Max Range: 4.5353. Min Range: -4.5353

Max Act: 3.8551. Min Act: -0.0000

Data Index: 920176 (The Pile)

Max Activating Token Index: 729

Text #15

Max Range: 4.5353. Min Range: -4.5353

Max Act: 3.4387. Min Act: -0.0000

Data Index: 1909735 (The Pile)

Max Activating Token Index: 281

Text #16

Max Range: 4.5353. Min Range: -4.5353

Max Act: 3.8478. Min Act: -0.0000

Data Index: 1517075 (The Pile)

Max Activating Token Index: 690

Text #17

Max Range: 4.5353. Min Range: -4.5353

Max Act: 3.7714. Min Act: -0.0000

Data Index: 500663 (The Pile)

Max Activating Token Index: 415

Text #18

Max Range: 4.5353. Min Range: -4.5353

Max Act: 3.9207. Min Act: -0.0000

Data Index: 689394 (The Pile)

Max Activating Token Index: 1003

Text #19

Max Range: 4.5353. Min Range: -4.5353

Max Act: 3.7437. Min Act: -0.0000

Data Index: 1961767 (The Pile)

Max Activating Token Index: 262