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

Dataset: The Pile

Neuron 2375 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1590. Min Range: -1.1590

Max Act: 1.1590. Min Act: -0.0000

Data Index: 1834783 (The Pile)

Max Activating Token Index: 737

Text #1

Max Range: 1.1590. Min Range: -1.1590

Max Act: 1.0549. Min Act: -0.0000

Data Index: 1593773 (The Pile)

Max Activating Token Index: 761

Text #2

Max Range: 1.1590. Min Range: -1.1590

Max Act: 1.0059. Min Act: -0.0000

Data Index: 416722 (The Pile)

Max Activating Token Index: 488

Text #3

Max Range: 1.1590. Min Range: -1.1590

Max Act: 1.0048. Min Act: -0.0000

Data Index: 417727 (The Pile)

Max Activating Token Index: 387

Text #4

Max Range: 1.1590. Min Range: -1.1590

Max Act: 0.9665. Min Act: -0.0000

Data Index: 1848059 (The Pile)

Max Activating Token Index: 938

Text #5

Max Range: 1.1590. Min Range: -1.1590

Max Act: 0.9336. Min Act: -0.0000

Data Index: 645250 (The Pile)

Max Activating Token Index: 1005

Text #6

Max Range: 1.1590. Min Range: -1.1590

Max Act: 0.9340. Min Act: -0.0000

Data Index: 963538 (The Pile)

Max Activating Token Index: 994

Text #7

Max Range: 1.1590. Min Range: -1.1590

Max Act: 0.8351. Min Act: -0.0000

Data Index: 1921939 (The Pile)

Max Activating Token Index: 1001

Text #8

Max Range: 1.1590. Min Range: -1.1590

Max Act: 0.8537. Min Act: -0.0000

Data Index: 1948305 (The Pile)

Max Activating Token Index: 660

Text #9

Max Range: 1.1590. Min Range: -1.1590

Max Act: 0.8166. Min Act: -0.0000

Data Index: 39682 (The Pile)

Max Activating Token Index: 272

Text #10

Max Range: 1.1590. Min Range: -1.1590

Max Act: 0.8755. Min Act: -0.0000

Data Index: 1470854 (The Pile)

Max Activating Token Index: 500

Text #11

Max Range: 1.1590. Min Range: -1.1590

Max Act: 0.8388. Min Act: -0.0000

Data Index: 1034642 (The Pile)

Max Activating Token Index: 412

Text #12

Max Range: 1.1590. Min Range: -1.1590

Max Act: 0.7881. Min Act: -0.0000

Data Index: 131484 (The Pile)

Max Activating Token Index: 686

Text #13

Max Range: 1.1590. Min Range: -1.1590

Max Act: 0.9275. Min Act: -0.0000

Data Index: 1504850 (The Pile)

Max Activating Token Index: 195

Text #14

Max Range: 1.1590. Min Range: -1.1590

Max Act: 0.8030. Min Act: -0.0000

Data Index: 180330 (The Pile)

Max Activating Token Index: 318

Text #15

Max Range: 1.1590. Min Range: -1.1590

Max Act: 0.8314. Min Act: -0.0000

Data Index: 1723006 (The Pile)

Max Activating Token Index: 800

Text #16

Max Range: 1.1590. Min Range: -1.1590

Max Act: 0.8614. Min Act: -0.0000

Data Index: 401975 (The Pile)

Max Activating Token Index: 751

Text #17

Max Range: 1.1590. Min Range: -1.1590

Max Act: 0.8096. Min Act: -0.0000

Data Index: 1410188 (The Pile)

Max Activating Token Index: 860

Text #18

Max Range: 1.1590. Min Range: -1.1590

Max Act: 0.8786. Min Act: -0.0000

Data Index: 1258823 (The Pile)

Max Activating Token Index: 18

Text #19

Max Range: 1.1590. Min Range: -1.1590

Max Act: 0.7973. Min Act: -0.0000

Data Index: 663276 (The Pile)

Max Activating Token Index: 523