Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3550 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.0731. Min Range: -1.0731

Max Act: 1.0731. Min Act: -0.0000

Data Index: 110092 (The Pile)

Max Activating Token Index: 151

Text #1

Max Range: 1.0731. Min Range: -1.0731

Max Act: 0.9985. Min Act: -0.0000

Data Index: 1003438 (The Pile)

Max Activating Token Index: 602

Text #2

Max Range: 1.0731. Min Range: -1.0731

Max Act: 0.9583. Min Act: -0.0000

Data Index: 681922 (The Pile)

Max Activating Token Index: 223

Text #3

Max Range: 1.0731. Min Range: -1.0731

Max Act: 0.9523. Min Act: -0.0000

Data Index: 965332 (The Pile)

Max Activating Token Index: 300

Text #4

Max Range: 1.0731. Min Range: -1.0731

Max Act: 0.8881. Min Act: -0.0000

Data Index: 1202395 (The Pile)

Max Activating Token Index: 158

Text #5

Max Range: 1.0731. Min Range: -1.0731

Max Act: 0.8849. Min Act: -0.0000

Data Index: 67562 (The Pile)

Max Activating Token Index: 136

Text #6

Max Range: 1.0731. Min Range: -1.0731

Max Act: 0.8390. Min Act: -0.0000

Data Index: 585612 (The Pile)

Max Activating Token Index: 1011

Text #7

Max Range: 1.0731. Min Range: -1.0731

Max Act: 0.8468. Min Act: -0.0000

Data Index: 1498019 (The Pile)

Max Activating Token Index: 354

Text #8

Max Range: 1.0731. Min Range: -1.0731

Max Act: 0.8272. Min Act: -0.0000

Data Index: 1981895 (The Pile)

Max Activating Token Index: 143

Text #9

Max Range: 1.0731. Min Range: -1.0731

Max Act: 0.8134. Min Act: 0.0000

Data Index: 1422770 (The Pile)

Max Activating Token Index: 889

Text #10

Max Range: 1.0731. Min Range: -1.0731

Max Act: 0.7952. Min Act: -0.0000

Data Index: 762418 (The Pile)

Max Activating Token Index: 763

Text #11

Max Range: 1.0731. Min Range: -1.0731

Max Act: 0.8596. Min Act: -0.0000

Data Index: 1093940 (The Pile)

Max Activating Token Index: 145

Text #12

Max Range: 1.0731. Min Range: -1.0731

Max Act: 0.8100. Min Act: -0.0000

Data Index: 531674 (The Pile)

Max Activating Token Index: 242

Text #13

Max Range: 1.0731. Min Range: -1.0731

Max Act: 0.7624. Min Act: -0.0000

Data Index: 1076158 (The Pile)

Max Activating Token Index: 55

Text #14

Max Range: 1.0731. Min Range: -1.0731

Max Act: 0.8072. Min Act: 0.0000

Data Index: 668164 (The Pile)

Max Activating Token Index: 286

Text #15

Max Range: 1.0731. Min Range: -1.0731

Max Act: 0.7336. Min Act: -0.0000

Data Index: 1613744 (The Pile)

Max Activating Token Index: 26

Text #16

Max Range: 1.0731. Min Range: -1.0731

Max Act: 0.7546. Min Act: -0.0000

Data Index: 1484784 (The Pile)

Max Activating Token Index: 807

Text #17

Max Range: 1.0731. Min Range: -1.0731

Max Act: 0.7485. Min Act: -0.0000

Data Index: 1032625 (The Pile)

Max Activating Token Index: 348

Text #18

Max Range: 1.0731. Min Range: -1.0731

Max Act: 0.7325. Min Act: -0.0000

Data Index: 984354 (The Pile)

Max Activating Token Index: 155

Text #19

Max Range: 1.0731. Min Range: -1.0731

Max Act: 0.7474. Min Act: -0.0000

Data Index: 659660 (The Pile)

Max Activating Token Index: 393