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

Dataset: The Pile

Neuron 477 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9802. Min Range: -0.9802

Max Act: 0.9802. Min Act: -0.0000

Data Index: 1221212 (The Pile)

Max Activating Token Index: 390

Text #1

Max Range: 0.9802. Min Range: -0.9802

Max Act: 0.9433. Min Act: -0.0000

Data Index: 40896 (The Pile)

Max Activating Token Index: 614

Text #2

Max Range: 0.9802. Min Range: -0.9802

Max Act: 0.7714. Min Act: -0.0000

Data Index: 1388557 (The Pile)

Max Activating Token Index: 505

Text #3

Max Range: 0.9802. Min Range: -0.9802

Max Act: 0.7759. Min Act: -0.0000

Data Index: 1542264 (The Pile)

Max Activating Token Index: 158

Text #4

Max Range: 0.9802. Min Range: -0.9802

Max Act: 0.7785. Min Act: -0.0000

Data Index: 1584299 (The Pile)

Max Activating Token Index: 787

Text #5

Max Range: 0.9802. Min Range: -0.9802

Max Act: 0.7923. Min Act: -0.0000

Data Index: 1543047 (The Pile)

Max Activating Token Index: 107

Text #6

Max Range: 0.9802. Min Range: -0.9802

Max Act: 0.7596. Min Act: -0.0000

Data Index: 304833 (The Pile)

Max Activating Token Index: 134

Text #7

Max Range: 0.9802. Min Range: -0.9802

Max Act: 0.7396. Min Act: -0.0000

Data Index: 1661163 (The Pile)

Max Activating Token Index: 486

Text #8

Max Range: 0.9802. Min Range: -0.9802

Max Act: 0.7491. Min Act: -0.0000

Data Index: 1338664 (The Pile)

Max Activating Token Index: 400

Text #9

Max Range: 0.9802. Min Range: -0.9802

Max Act: 0.6876. Min Act: -0.0000

Data Index: 108819 (The Pile)

Max Activating Token Index: 525

Text #10

Max Range: 0.9802. Min Range: -0.9802

Max Act: 0.7177. Min Act: -0.0000

Data Index: 52273 (The Pile)

Max Activating Token Index: 499

Text #11

Max Range: 0.9802. Min Range: -0.9802

Max Act: 0.7173. Min Act: -0.0000

Data Index: 1662421 (The Pile)

Max Activating Token Index: 587

Text #12

Max Range: 0.9802. Min Range: -0.9802

Max Act: 0.6851. Min Act: 0.0001

Data Index: 1870188 (The Pile)

Max Activating Token Index: 1007

Text #13

Max Range: 0.9802. Min Range: -0.9802

Max Act: 0.7104. Min Act: -0.0000

Data Index: 203922 (The Pile)

Max Activating Token Index: 183

Text #14

Max Range: 0.9802. Min Range: -0.9802

Max Act: 0.6802. Min Act: -0.0000

Data Index: 1338620 (The Pile)

Max Activating Token Index: 336

Text #15

Max Range: 0.9802. Min Range: -0.9802

Max Act: 0.6535. Min Act: -0.0000

Data Index: 109152 (The Pile)

Max Activating Token Index: 187

Text #16

Max Range: 0.9802. Min Range: -0.9802

Max Act: 0.7130. Min Act: -0.0000

Data Index: 1314416 (The Pile)

Max Activating Token Index: 64

Text #17

Max Range: 0.9802. Min Range: -0.9802

Max Act: 0.7088. Min Act: -0.0000

Data Index: 745736 (The Pile)

Max Activating Token Index: 849

Text #18

Max Range: 0.9802. Min Range: -0.9802

Max Act: 0.6674. Min Act: -0.0000

Data Index: 1194436 (The Pile)

Max Activating Token Index: 579

Text #19

Max Range: 0.9802. Min Range: -0.9802

Max Act: 0.6581. Min Act: 0.0000

Data Index: 1024806 (The Pile)

Max Activating Token Index: 926