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

Dataset: The Pile

Neuron 651 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3938. Min Range: -1.3938

Max Act: 1.3938. Min Act: -0.0000

Data Index: 1578765 (The Pile)

Max Activating Token Index: 854

Text #1

Max Range: 1.3938. Min Range: -1.3938

Max Act: 1.1506. Min Act: -0.0000

Data Index: 973316 (The Pile)

Max Activating Token Index: 681

Text #2

Max Range: 1.3938. Min Range: -1.3938

Max Act: 1.2149. Min Act: -0.0000

Data Index: 1885019 (The Pile)

Max Activating Token Index: 289

Text #3

Max Range: 1.3938. Min Range: -1.3938

Max Act: 1.1364. Min Act: -0.0000

Data Index: 789039 (The Pile)

Max Activating Token Index: 804

Text #4

Max Range: 1.3938. Min Range: -1.3938

Max Act: 1.1773. Min Act: -0.0000

Data Index: 1334541 (The Pile)

Max Activating Token Index: 227

Text #5

Max Range: 1.3938. Min Range: -1.3938

Max Act: 1.0720. Min Act: -0.0000

Data Index: 1092239 (The Pile)

Max Activating Token Index: 997

Text #6

Max Range: 1.3938. Min Range: -1.3938

Max Act: 1.2022. Min Act: -0.0000

Data Index: 1817824 (The Pile)

Max Activating Token Index: 289

Text #7

Max Range: 1.3938. Min Range: -1.3938

Max Act: 1.0406. Min Act: -0.0000

Data Index: 1745321 (The Pile)

Max Activating Token Index: 950

Text #8

Max Range: 1.3938. Min Range: -1.3938

Max Act: 1.0695. Min Act: -0.0000

Data Index: 46948 (The Pile)

Max Activating Token Index: 156

Text #9

Max Range: 1.3938. Min Range: -1.3938

Max Act: 1.0578. Min Act: -0.0000

Data Index: 855546 (The Pile)

Max Activating Token Index: 324

Text #10

Max Range: 1.3938. Min Range: -1.3938

Max Act: 1.0263. Min Act: -0.0000

Data Index: 1690336 (The Pile)

Max Activating Token Index: 120

Text #11

Max Range: 1.3938. Min Range: -1.3938

Max Act: 1.0072. Min Act: -0.0000

Data Index: 1333470 (The Pile)

Max Activating Token Index: 81

Text #12

Max Range: 1.3938. Min Range: -1.3938

Max Act: 0.9658. Min Act: -0.0000

Data Index: 350437 (The Pile)

Max Activating Token Index: 882

Text #13

Max Range: 1.3938. Min Range: -1.3938

Max Act: 0.9786. Min Act: -0.0000

Data Index: 1389951 (The Pile)

Max Activating Token Index: 169

Text #14

Max Range: 1.3938. Min Range: -1.3938

Max Act: 0.9712. Min Act: -0.0000

Data Index: 984257 (The Pile)

Max Activating Token Index: 147

Text #15

Max Range: 1.3938. Min Range: -1.3938

Max Act: 0.9756. Min Act: -0.0000

Data Index: 931312 (The Pile)

Max Activating Token Index: 583

Text #16

Max Range: 1.3938. Min Range: -1.3938

Max Act: 0.9402. Min Act: -0.0000

Data Index: 511997 (The Pile)

Max Activating Token Index: 951

Text #17

Max Range: 1.3938. Min Range: -1.3938

Max Act: 0.9273. Min Act: -0.0000

Data Index: 1687313 (The Pile)

Max Activating Token Index: 402

Text #18

Max Range: 1.3938. Min Range: -1.3938

Max Act: 0.9251. Min Act: -0.0000

Data Index: 638915 (The Pile)

Max Activating Token Index: 558

Text #19

Max Range: 1.3938. Min Range: -1.3938

Max Act: 0.9464. Min Act: 0.0000

Data Index: 716371 (The Pile)

Max Activating Token Index: 911