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

Dataset: The Pile

Neuron 1044 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9479. Min Range: -1.9479

Max Act: 1.8736. Min Act: -0.0000

Data Index: 315656 (The Pile)

Max Activating Token Index: 365

Text #1

Max Range: 1.9479. Min Range: -1.9479

Max Act: 1.9209. Min Act: -0.0000

Data Index: 1440067 (The Pile)

Max Activating Token Index: 760

Text #2

Max Range: 1.9479. Min Range: -1.9479

Max Act: 1.9023. Min Act: -0.0000

Data Index: 711726 (The Pile)

Max Activating Token Index: 463

Text #3

Max Range: 1.9479. Min Range: -1.9479

Max Act: 1.8947. Min Act: -0.0000

Data Index: 68607 (The Pile)

Max Activating Token Index: 333

Text #4

Max Range: 1.9479. Min Range: -1.9479

Max Act: 1.7765. Min Act: -0.0000

Data Index: 306778 (The Pile)

Max Activating Token Index: 174

Text #5

Max Range: 1.9479. Min Range: -1.9479

Max Act: 1.8501. Min Act: -0.0000

Data Index: 1263424 (The Pile)

Max Activating Token Index: 612

Text #6

Max Range: 1.9479. Min Range: -1.9479

Max Act: 1.8498. Min Act: -0.0000

Data Index: 1219494 (The Pile)

Max Activating Token Index: 398

Text #7

Max Range: 1.9479. Min Range: -1.9479

Max Act: 1.8373. Min Act: -0.0000

Data Index: 294479 (The Pile)

Max Activating Token Index: 276

Text #8

Max Range: 1.9479. Min Range: -1.9479

Max Act: 1.7263. Min Act: -0.0000

Data Index: 711429 (The Pile)

Max Activating Token Index: 537

Text #9

Max Range: 1.9479. Min Range: -1.9479

Max Act: 1.9479. Min Act: -0.0000

Data Index: 954941 (The Pile)

Max Activating Token Index: 165

Text #10

Max Range: 1.9479. Min Range: -1.9479

Max Act: 1.7208. Min Act: -0.0000

Data Index: 1542640 (The Pile)

Max Activating Token Index: 647

Text #11

Max Range: 1.9479. Min Range: -1.9479

Max Act: 1.9046. Min Act: -0.0000

Data Index: 340192 (The Pile)

Max Activating Token Index: 891

Text #12

Max Range: 1.9479. Min Range: -1.9479

Max Act: 1.8098. Min Act: -0.0000

Data Index: 1335214 (The Pile)

Max Activating Token Index: 558

Text #13

Max Range: 1.9479. Min Range: -1.9479

Max Act: 1.6923. Min Act: -0.0000

Data Index: 1697233 (The Pile)

Max Activating Token Index: 173

Text #14

Max Range: 1.9479. Min Range: -1.9479

Max Act: 1.6758. Min Act: -0.0000

Data Index: 1209928 (The Pile)

Max Activating Token Index: 475

Text #15

Max Range: 1.9479. Min Range: -1.9479

Max Act: 1.7486. Min Act: -0.0000

Data Index: 1579528 (The Pile)

Max Activating Token Index: 573

Text #16

Max Range: 1.9479. Min Range: -1.9479

Max Act: 1.6625. Min Act: -0.0000

Data Index: 1751710 (The Pile)

Max Activating Token Index: 60

Text #17

Max Range: 1.9479. Min Range: -1.9479

Max Act: 1.7370. Min Act: -0.0000

Data Index: 1180688 (The Pile)

Max Activating Token Index: 136

Text #18

Max Range: 1.9479. Min Range: -1.9479

Max Act: 1.7215. Min Act: -0.0000

Data Index: 1676260 (The Pile)

Max Activating Token Index: 760

Text #19

Max Range: 1.9479. Min Range: -1.9479

Max Act: 1.8043. Min Act: -0.0000

Data Index: 1418510 (The Pile)

Max Activating Token Index: 105