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

Dataset: The Pile

Neuron 2613 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: 0.8411. Min Range: -0.8411

Max Act: 0.8411. Min Act: -0.0000

Data Index: 1284317 (The Pile)

Max Activating Token Index: 979

Text #1

Max Range: 0.8411. Min Range: -0.8411

Max Act: 0.7826. Min Act: -0.0000

Data Index: 1236291 (The Pile)

Max Activating Token Index: 837

Text #2

Max Range: 0.8411. Min Range: -0.8411

Max Act: 0.7625. Min Act: -0.0000

Data Index: 1000907 (The Pile)

Max Activating Token Index: 425

Text #3

Max Range: 0.8411. Min Range: -0.8411

Max Act: 0.6923. Min Act: -0.0000

Data Index: 1146438 (The Pile)

Max Activating Token Index: 343

Text #4

Max Range: 0.8411. Min Range: -0.8411

Max Act: 0.6790. Min Act: -0.0000

Data Index: 1826896 (The Pile)

Max Activating Token Index: 73

Text #5

Max Range: 0.8411. Min Range: -0.8411

Max Act: 0.6836. Min Act: -0.0000

Data Index: 378787 (The Pile)

Max Activating Token Index: 589

Text #6

Max Range: 0.8411. Min Range: -0.8411

Max Act: 0.6387. Min Act: -0.0000

Data Index: 896323 (The Pile)

Max Activating Token Index: 234

Text #7

Max Range: 0.8411. Min Range: -0.8411

Max Act: 0.6012. Min Act: -0.0000

Data Index: 441564 (The Pile)

Max Activating Token Index: 630

Text #8

Max Range: 0.8411. Min Range: -0.8411

Max Act: 0.6337. Min Act: -0.0000

Data Index: 1726126 (The Pile)

Max Activating Token Index: 229

Text #9

Max Range: 0.8411. Min Range: -0.8411

Max Act: 0.6013. Min Act: -0.0000

Data Index: 1155251 (The Pile)

Max Activating Token Index: 378

Text #10

Max Range: 0.8411. Min Range: -0.8411

Max Act: 0.6199. Min Act: -0.0000

Data Index: 489658 (The Pile)

Max Activating Token Index: 940

Text #11

Max Range: 0.8411. Min Range: -0.8411

Max Act: 0.6199. Min Act: -0.0000

Data Index: 404664 (The Pile)

Max Activating Token Index: 128

Text #12

Max Range: 0.8411. Min Range: -0.8411

Max Act: 0.6144. Min Act: -0.0000

Data Index: 1816365 (The Pile)

Max Activating Token Index: 100

Text #13

Max Range: 0.8411. Min Range: -0.8411

Max Act: 0.5382. Min Act: -0.0000

Data Index: 66430 (The Pile)

Max Activating Token Index: 113

Text #14

Max Range: 0.8411. Min Range: -0.8411

Max Act: 0.5553. Min Act: -0.0000

Data Index: 1989550 (The Pile)

Max Activating Token Index: 172

Text #15

Max Range: 0.8411. Min Range: -0.8411

Max Act: 0.4822. Min Act: -0.0000

Data Index: 1118505 (The Pile)

Max Activating Token Index: 623

Text #16

Max Range: 0.8411. Min Range: -0.8411

Max Act: 0.5803. Min Act: -0.0000

Data Index: 945561 (The Pile)

Max Activating Token Index: 183

Text #17

Max Range: 0.8411. Min Range: -0.8411

Max Act: 0.5326. Min Act: -0.0000

Data Index: 141409 (The Pile)

Max Activating Token Index: 675

Text #18

Max Range: 0.8411. Min Range: -0.8411

Max Act: 0.5288. Min Act: -0.0000

Data Index: 935514 (The Pile)

Max Activating Token Index: 667

Text #19

Max Range: 0.8411. Min Range: -0.8411

Max Act: 0.5565. Min Act: -0.0000

Data Index: 1330973 (The Pile)

Max Activating Token Index: 624