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

Dataset: The Pile

Neuron 157 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5669. Min Range: -1.5669

Max Act: 1.5669. Min Act: -0.0000

Data Index: 1230682 (The Pile)

Max Activating Token Index: 988

Text #1

Max Range: 1.5669. Min Range: -1.5669

Max Act: 1.5536. Min Act: -0.0000

Data Index: 1654406 (The Pile)

Max Activating Token Index: 834

Text #2

Max Range: 1.5669. Min Range: -1.5669

Max Act: 1.3992. Min Act: -0.0000

Data Index: 1701433 (The Pile)

Max Activating Token Index: 471

Text #3

Max Range: 1.5669. Min Range: -1.5669

Max Act: 1.2713. Min Act: -0.0000

Data Index: 1325290 (The Pile)

Max Activating Token Index: 750

Text #4

Max Range: 1.5669. Min Range: -1.5669

Max Act: 1.1017. Min Act: -0.0000

Data Index: 352280 (The Pile)

Max Activating Token Index: 836

Text #5

Max Range: 1.5669. Min Range: -1.5669

Max Act: 1.1001. Min Act: -0.0000

Data Index: 1235000 (The Pile)

Max Activating Token Index: 481

Text #6

Max Range: 1.5669. Min Range: -1.5669

Max Act: 0.9122. Min Act: -0.0000

Data Index: 1785359 (The Pile)

Max Activating Token Index: 971

Text #7

Max Range: 1.5669. Min Range: -1.5669

Max Act: 1.1064. Min Act: -0.0000

Data Index: 65193 (The Pile)

Max Activating Token Index: 863

Text #8

Max Range: 1.5669. Min Range: -1.5669

Max Act: 1.0576. Min Act: -0.0000

Data Index: 437874 (The Pile)

Max Activating Token Index: 637

Text #9

Max Range: 1.5669. Min Range: -1.5669

Max Act: 1.3444. Min Act: -0.0000

Data Index: 150583 (The Pile)

Max Activating Token Index: 722

Text #10

Max Range: 1.5669. Min Range: -1.5669

Max Act: 1.0868. Min Act: -0.0000

Data Index: 143864 (The Pile)

Max Activating Token Index: 646

Text #11

Max Range: 1.5669. Min Range: -1.5669

Max Act: 1.0416. Min Act: -0.0000

Data Index: 346170 (The Pile)

Max Activating Token Index: 146

Text #12

Max Range: 1.5669. Min Range: -1.5669

Max Act: 0.9582. Min Act: -0.0000

Data Index: 1646726 (The Pile)

Max Activating Token Index: 788

Text #13

Max Range: 1.5669. Min Range: -1.5669

Max Act: 0.9499. Min Act: -0.0000

Data Index: 1860914 (The Pile)

Max Activating Token Index: 989

Text #14

Max Range: 1.5669. Min Range: -1.5669

Max Act: 0.9795. Min Act: -0.0000

Data Index: 164371 (The Pile)

Max Activating Token Index: 869

Text #15

Max Range: 1.5669. Min Range: -1.5669

Max Act: 0.9212. Min Act: -0.0000

Data Index: 464635 (The Pile)

Max Activating Token Index: 1010

Text #16

Max Range: 1.5669. Min Range: -1.5669

Max Act: 0.9322. Min Act: -0.0000

Data Index: 1142956 (The Pile)

Max Activating Token Index: 543

Text #17

Max Range: 1.5669. Min Range: -1.5669

Max Act: 0.8553. Min Act: -0.0000

Data Index: 788472 (The Pile)

Max Activating Token Index: 808

Text #18

Max Range: 1.5669. Min Range: -1.5669

Max Act: 0.8692. Min Act: -0.0000

Data Index: 1001523 (The Pile)

Max Activating Token Index: 675

Text #19

Max Range: 1.5669. Min Range: -1.5669

Max Act: 0.6398. Min Act: -0.0000

Data Index: 1193964 (The Pile)

Max Activating Token Index: 842