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

Dataset: The Pile

Neuron 4449 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1038. Min Range: -1.1038

Max Act: 1.1038. Min Act: -0.0001

Data Index: 138553 (The Pile)

Max Activating Token Index: 46

Text #1

Max Range: 1.1038. Min Range: -1.1038

Max Act: 1.0287. Min Act: -0.0001

Data Index: 494027 (The Pile)

Max Activating Token Index: 881

Text #2

Max Range: 1.1038. Min Range: -1.1038

Max Act: 1.0553. Min Act: -0.0001

Data Index: 676967 (The Pile)

Max Activating Token Index: 942

Text #3

Max Range: 1.1038. Min Range: -1.1038

Max Act: 1.0142. Min Act: -0.0001

Data Index: 1976349 (The Pile)

Max Activating Token Index: 221

Text #4

Max Range: 1.1038. Min Range: -1.1038

Max Act: 1.0691. Min Act: -0.0001

Data Index: 714500 (The Pile)

Max Activating Token Index: 1006

Text #5

Max Range: 1.1038. Min Range: -1.1038

Max Act: 0.9889. Min Act: -0.0001

Data Index: 427263 (The Pile)

Max Activating Token Index: 856

Text #6

Max Range: 1.1038. Min Range: -1.1038

Max Act: 1.0431. Min Act: -0.0000

Data Index: 374517 (The Pile)

Max Activating Token Index: 547

Text #7

Max Range: 1.1038. Min Range: -1.1038

Max Act: 1.0037. Min Act: -0.0001

Data Index: 452702 (The Pile)

Max Activating Token Index: 295

Text #8

Max Range: 1.1038. Min Range: -1.1038

Max Act: 0.9990. Min Act: -0.0001

Data Index: 98027 (The Pile)

Max Activating Token Index: 260

Text #9

Max Range: 1.1038. Min Range: -1.1038

Max Act: 0.9923. Min Act: -0.0001

Data Index: 46443 (The Pile)

Max Activating Token Index: 260

Text #10

Max Range: 1.1038. Min Range: -1.1038

Max Act: 0.9729. Min Act: -0.0001

Data Index: 1643989 (The Pile)

Max Activating Token Index: 813

Text #11

Max Range: 1.1038. Min Range: -1.1038

Max Act: 0.9871. Min Act: -0.0001

Data Index: 1085726 (The Pile)

Max Activating Token Index: 120

Text #12

Max Range: 1.1038. Min Range: -1.1038

Max Act: 0.9810. Min Act: -0.0001

Data Index: 89021 (The Pile)

Max Activating Token Index: 7

Text #13

Max Range: 1.1038. Min Range: -1.1038

Max Act: 0.9472. Min Act: -0.0001

Data Index: 1859130 (The Pile)

Max Activating Token Index: 419

Text #14

Max Range: 1.1038. Min Range: -1.1038

Max Act: 0.9670. Min Act: -0.0000

Data Index: 1269269 (The Pile)

Max Activating Token Index: 353

Text #15

Max Range: 1.1038. Min Range: -1.1038

Max Act: 0.9399. Min Act: -0.0001

Data Index: 1008315 (The Pile)

Max Activating Token Index: 976

Text #16

Max Range: 1.1038. Min Range: -1.1038

Max Act: 0.9330. Min Act: -0.0001

Data Index: 1143801 (The Pile)

Max Activating Token Index: 476

Text #17

Max Range: 1.1038. Min Range: -1.1038

Max Act: 0.9009. Min Act: -0.0001

Data Index: 519466 (The Pile)

Max Activating Token Index: 840

Text #18

Max Range: 1.1038. Min Range: -1.1038

Max Act: 0.9552. Min Act: -0.0001

Data Index: 231773 (The Pile)

Max Activating Token Index: 325

Text #19

Max Range: 1.1038. Min Range: -1.1038

Max Act: 0.9147. Min Act: -0.0001

Data Index: 1250883 (The Pile)

Max Activating Token Index: 966