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

Dataset: The Pile

Neuron 3362 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9882. Min Range: -0.9882

Max Act: 0.9882. Min Act: -0.0000

Data Index: 1375625 (The Pile)

Max Activating Token Index: 791

Text #1

Max Range: 0.9882. Min Range: -0.9882

Max Act: 0.9480. Min Act: -0.0000

Data Index: 1553976 (The Pile)

Max Activating Token Index: 750

Text #2

Max Range: 0.9882. Min Range: -0.9882

Max Act: 0.9239. Min Act: -0.0000

Data Index: 1756585 (The Pile)

Max Activating Token Index: 657

Text #3

Max Range: 0.9882. Min Range: -0.9882

Max Act: 0.8968. Min Act: -0.0000

Data Index: 1068375 (The Pile)

Max Activating Token Index: 584

Text #4

Max Range: 0.9882. Min Range: -0.9882

Max Act: 0.8953. Min Act: -0.0000

Data Index: 136436 (The Pile)

Max Activating Token Index: 195

Text #5

Max Range: 0.9882. Min Range: -0.9882

Max Act: 0.9101. Min Act: -0.0000

Data Index: 1163838 (The Pile)

Max Activating Token Index: 238

Text #6

Max Range: 0.9882. Min Range: -0.9882

Max Act: 0.9050. Min Act: -0.0000

Data Index: 140190 (The Pile)

Max Activating Token Index: 519

Text #7

Max Range: 0.9882. Min Range: -0.9882

Max Act: 0.8738. Min Act: -0.0000

Data Index: 407460 (The Pile)

Max Activating Token Index: 953

Text #8

Max Range: 0.9882. Min Range: -0.9882

Max Act: 0.8371. Min Act: -0.0000

Data Index: 982180 (The Pile)

Max Activating Token Index: 929

Text #9

Max Range: 0.9882. Min Range: -0.9882

Max Act: 0.8819. Min Act: -0.0000

Data Index: 893445 (The Pile)

Max Activating Token Index: 99

Text #10

Max Range: 0.9882. Min Range: -0.9882

Max Act: 0.7722. Min Act: -0.0000

Data Index: 1299858 (The Pile)

Max Activating Token Index: 603

Text #11

Max Range: 0.9882. Min Range: -0.9882

Max Act: 0.8367. Min Act: -0.0000

Data Index: 602050 (The Pile)

Max Activating Token Index: 279

Text #12

Max Range: 0.9882. Min Range: -0.9882

Max Act: 0.8593. Min Act: -0.0000

Data Index: 70304 (The Pile)

Max Activating Token Index: 157

Text #13

Max Range: 0.9882. Min Range: -0.9882

Max Act: 0.7925. Min Act: -0.0000

Data Index: 1311934 (The Pile)

Max Activating Token Index: 729

Text #14

Max Range: 0.9882. Min Range: -0.9882

Max Act: 0.8442. Min Act: -0.0000

Data Index: 831774 (The Pile)

Max Activating Token Index: 999

Text #15

Max Range: 0.9882. Min Range: -0.9882

Max Act: 0.7861. Min Act: -0.0000

Data Index: 793342 (The Pile)

Max Activating Token Index: 63

Text #16

Max Range: 0.9882. Min Range: -0.9882

Max Act: 0.7839. Min Act: -0.0000

Data Index: 1917544 (The Pile)

Max Activating Token Index: 521

Text #17

Max Range: 0.9882. Min Range: -0.9882

Max Act: 0.8060. Min Act: -0.0000

Data Index: 465752 (The Pile)

Max Activating Token Index: 141

Text #18

Max Range: 0.9882. Min Range: -0.9882

Max Act: 0.7748. Min Act: -0.0000

Data Index: 1861871 (The Pile)

Max Activating Token Index: 335

Text #19

Max Range: 0.9882. Min Range: -0.9882

Max Act: 0.7956. Min Act: -0.0000

Data Index: 868238 (The Pile)

Max Activating Token Index: 40