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

Dataset: The Pile

Neuron 3442 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: 1.1925. Min Range: -1.1925

Max Act: 1.1925. Min Act: -0.0000

Data Index: 1214580 (The Pile)

Max Activating Token Index: 997

Text #1

Max Range: 1.1925. Min Range: -1.1925

Max Act: 1.0359. Min Act: -0.0000

Data Index: 524305 (The Pile)

Max Activating Token Index: 39

Text #2

Max Range: 1.1925. Min Range: -1.1925

Max Act: 0.9581. Min Act: 0.0000

Data Index: 469691 (The Pile)

Max Activating Token Index: 690

Text #3

Max Range: 1.1925. Min Range: -1.1925

Max Act: 0.9503. Min Act: -0.0000

Data Index: 1463212 (The Pile)

Max Activating Token Index: 311

Text #4

Max Range: 1.1925. Min Range: -1.1925

Max Act: 0.9450. Min Act: -0.0000

Data Index: 528672 (The Pile)

Max Activating Token Index: 423

Text #5

Max Range: 1.1925. Min Range: -1.1925

Max Act: 0.9341. Min Act: -0.0000

Data Index: 1413206 (The Pile)

Max Activating Token Index: 127

Text #6

Max Range: 1.1925. Min Range: -1.1925

Max Act: 0.9319. Min Act: -0.0000

Data Index: 1430498 (The Pile)

Max Activating Token Index: 824

Text #7

Max Range: 1.1925. Min Range: -1.1925

Max Act: 0.9272. Min Act: -0.0000

Data Index: 965786 (The Pile)

Max Activating Token Index: 563

Text #8

Max Range: 1.1925. Min Range: -1.1925

Max Act: 0.8650. Min Act: 0.0000

Data Index: 1226913 (The Pile)

Max Activating Token Index: 8

Text #9

Max Range: 1.1925. Min Range: -1.1925

Max Act: 0.9625. Min Act: 0.0000

Data Index: 949070 (The Pile)

Max Activating Token Index: 8

Text #10

Max Range: 1.1925. Min Range: -1.1925

Max Act: 0.9029. Min Act: 0.0000

Data Index: 154035 (The Pile)

Max Activating Token Index: 379

Text #11

Max Range: 1.1925. Min Range: -1.1925

Max Act: 0.8457. Min Act: 0.0001

Data Index: 1441543 (The Pile)

Max Activating Token Index: 12

Text #12

Max Range: 1.1925. Min Range: -1.1925

Max Act: 0.8915. Min Act: 0.0000

Data Index: 1962957 (The Pile)

Max Activating Token Index: 96

Text #13

Max Range: 1.1925. Min Range: -1.1925

Max Act: 0.9447. Min Act: -0.0000

Data Index: 701011 (The Pile)

Max Activating Token Index: 850

Text #14

Max Range: 1.1925. Min Range: -1.1925

Max Act: 0.8906. Min Act: -0.0000

Data Index: 686963 (The Pile)

Max Activating Token Index: 587

Text #15

Max Range: 1.1925. Min Range: -1.1925

Max Act: 0.8786. Min Act: -0.0000

Data Index: 38046 (The Pile)

Max Activating Token Index: 70

Text #16

Max Range: 1.1925. Min Range: -1.1925

Max Act: 0.8325. Min Act: -0.0000

Data Index: 1077184 (The Pile)

Max Activating Token Index: 373

Text #17

Max Range: 1.1925. Min Range: -1.1925

Max Act: 0.9512. Min Act: -0.0000

Data Index: 696671 (The Pile)

Max Activating Token Index: 904

Text #18

Max Range: 1.1925. Min Range: -1.1925

Max Act: 0.8219. Min Act: 0.0000

Data Index: 1572014 (The Pile)

Max Activating Token Index: 519

Text #19

Max Range: 1.1925. Min Range: -1.1925

Max Act: 0.8102. Min Act: 0.0000

Data Index: 1514158 (The Pile)

Max Activating Token Index: 1022