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

Dataset: The Pile

Neuron 121 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: 0.4329. Min Range: -0.4329

Max Act: 0.4329. Min Act: -0.0000

Data Index: 396977 (The Pile)

Max Activating Token Index: 658

Text #1

Max Range: 0.4329. Min Range: -0.4329

Max Act: 0.3434. Min Act: -0.0000

Data Index: 929220 (The Pile)

Max Activating Token Index: 162

Text #2

Max Range: 0.4329. Min Range: -0.4329

Max Act: 0.3593. Min Act: -0.0000

Data Index: 1756049 (The Pile)

Max Activating Token Index: 511

Text #3

Max Range: 0.4329. Min Range: -0.4329

Max Act: 0.3130. Min Act: -0.0000

Data Index: 1773753 (The Pile)

Max Activating Token Index: 649

Text #4

Max Range: 0.4329. Min Range: -0.4329

Max Act: 0.3974. Min Act: -0.0000

Data Index: 832549 (The Pile)

Max Activating Token Index: 677

Text #5

Max Range: 0.4329. Min Range: -0.4329

Max Act: 0.3413. Min Act: -0.0000

Data Index: 7775 (The Pile)

Max Activating Token Index: 628

Text #6

Max Range: 0.4329. Min Range: -0.4329

Max Act: 0.3888. Min Act: -0.0000

Data Index: 937080 (The Pile)

Max Activating Token Index: 151

Text #7

Max Range: 0.4329. Min Range: -0.4329

Max Act: 0.4115. Min Act: -0.0000

Data Index: 986364 (The Pile)

Max Activating Token Index: 550

Text #8

Max Range: 0.4329. Min Range: -0.4329

Max Act: 0.2812. Min Act: -0.0000

Data Index: 569925 (The Pile)

Max Activating Token Index: 565

Text #9

Max Range: 0.4329. Min Range: -0.4329

Max Act: 0.3335. Min Act: -0.0000

Data Index: 143911 (The Pile)

Max Activating Token Index: 403

Text #10

Max Range: 0.4329. Min Range: -0.4329

Max Act: 0.2936. Min Act: -0.0000

Data Index: 1800116 (The Pile)

Max Activating Token Index: 526

Text #11

Max Range: 0.4329. Min Range: -0.4329

Max Act: 0.2713. Min Act: -0.0000

Data Index: 1599564 (The Pile)

Max Activating Token Index: 464

Text #12

Max Range: 0.4329. Min Range: -0.4329

Max Act: 0.2962. Min Act: -0.0000

Data Index: 1808269 (The Pile)

Max Activating Token Index: 763

Text #13

Max Range: 0.4329. Min Range: -0.4329

Max Act: 0.2880. Min Act: -0.0000

Data Index: 1405928 (The Pile)

Max Activating Token Index: 632

Text #14

Max Range: 0.4329. Min Range: -0.4329

Max Act: 0.3335. Min Act: -0.0000

Data Index: 594305 (The Pile)

Max Activating Token Index: 547

Text #15

Max Range: 0.4329. Min Range: -0.4329

Max Act: 0.3213. Min Act: -0.0000

Data Index: 1040405 (The Pile)

Max Activating Token Index: 448

Text #16

Max Range: 0.4329. Min Range: -0.4329

Max Act: 0.2550. Min Act: -0.0000

Data Index: 1157138 (The Pile)

Max Activating Token Index: 655

Text #17

Max Range: 0.4329. Min Range: -0.4329

Max Act: 0.2817. Min Act: -0.0000

Data Index: 1823081 (The Pile)

Max Activating Token Index: 726

Text #18

Max Range: 0.4329. Min Range: -0.4329

Max Act: 0.2955. Min Act: -0.0000

Data Index: 968129 (The Pile)

Max Activating Token Index: 664

Text #19

Max Range: 0.4329. Min Range: -0.4329

Max Act: 0.2750. Min Act: -0.0000

Data Index: 1748204 (The Pile)

Max Activating Token Index: 347