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

Dataset: The Pile

Neuron 1996 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: 3.5528. Min Range: -3.5528

Max Act: 3.2603. Min Act: -0.0000

Data Index: 1572088 (The Pile)

Max Activating Token Index: 935

Text #1

Max Range: 3.5528. Min Range: -3.5528

Max Act: 3.5528. Min Act: -0.0000

Data Index: 1397030 (The Pile)

Max Activating Token Index: 419

Text #2

Max Range: 3.5528. Min Range: -3.5528

Max Act: 3.2531. Min Act: -0.0000

Data Index: 802837 (The Pile)

Max Activating Token Index: 820

Text #3

Max Range: 3.5528. Min Range: -3.5528

Max Act: 3.3138. Min Act: -0.0000

Data Index: 1409923 (The Pile)

Max Activating Token Index: 366

Text #4

Max Range: 3.5528. Min Range: -3.5528

Max Act: 2.8666. Min Act: -0.0000

Data Index: 1997657 (The Pile)

Max Activating Token Index: 595

Text #5

Max Range: 3.5528. Min Range: -3.5528

Max Act: 2.8463. Min Act: -0.0000

Data Index: 1951749 (The Pile)

Max Activating Token Index: 268

Text #6

Max Range: 3.5528. Min Range: -3.5528

Max Act: 3.0804. Min Act: -0.0000

Data Index: 191637 (The Pile)

Max Activating Token Index: 966

Text #7

Max Range: 3.5528. Min Range: -3.5528

Max Act: 2.8936. Min Act: -0.0000

Data Index: 604018 (The Pile)

Max Activating Token Index: 29

Text #8

Max Range: 3.5528. Min Range: -3.5528

Max Act: 2.8618. Min Act: -0.0000

Data Index: 821979 (The Pile)

Max Activating Token Index: 629

Text #9

Max Range: 3.5528. Min Range: -3.5528

Max Act: 2.9714. Min Act: -0.0000

Data Index: 583878 (The Pile)

Max Activating Token Index: 526

Text #10

Max Range: 3.5528. Min Range: -3.5528

Max Act: 2.5337. Min Act: -0.0000

Data Index: 1217151 (The Pile)

Max Activating Token Index: 36

Text #11

Max Range: 3.5528. Min Range: -3.5528

Max Act: 2.7688. Min Act: -0.0000

Data Index: 548604 (The Pile)

Max Activating Token Index: 347

Text #12

Max Range: 3.5528. Min Range: -3.5528

Max Act: 2.2703. Min Act: -0.0000

Data Index: 1331157 (The Pile)

Max Activating Token Index: 1020

Text #13

Max Range: 3.5528. Min Range: -3.5528

Max Act: 2.3533. Min Act: -0.0000

Data Index: 576393 (The Pile)

Max Activating Token Index: 203

Text #14

Max Range: 3.5528. Min Range: -3.5528

Max Act: 2.4829. Min Act: -0.0000

Data Index: 346396 (The Pile)

Max Activating Token Index: 932

Text #15

Max Range: 3.5528. Min Range: -3.5528

Max Act: 2.8151. Min Act: -0.0000

Data Index: 80009 (The Pile)

Max Activating Token Index: 867

Text #16

Max Range: 3.5528. Min Range: -3.5528

Max Act: 2.5014. Min Act: -0.0000

Data Index: 145696 (The Pile)

Max Activating Token Index: 72

Text #17

Max Range: 3.5528. Min Range: -3.5528

Max Act: 2.1231. Min Act: -0.0000

Data Index: 1279767 (The Pile)

Max Activating Token Index: 51

Text #18

Max Range: 3.5528. Min Range: -3.5528

Max Act: 2.8347. Min Act: -0.0000

Data Index: 1679055 (The Pile)

Max Activating Token Index: 753

Text #19

Max Range: 3.5528. Min Range: -3.5528

Max Act: 2.8360. Min Act: -0.0000

Data Index: 437372 (The Pile)

Max Activating Token Index: 649