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

Dataset: The Pile

Neuron 899 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: 0.9754. Min Range: -0.9754

Max Act: 0.9754. Min Act: -0.0000

Data Index: 200755 (The Pile)

Max Activating Token Index: 199

Text #1

Max Range: 0.9754. Min Range: -0.9754

Max Act: 0.9392. Min Act: -0.0000

Data Index: 1987957 (The Pile)

Max Activating Token Index: 587

Text #2

Max Range: 0.9754. Min Range: -0.9754

Max Act: 0.9071. Min Act: -0.0000

Data Index: 428370 (The Pile)

Max Activating Token Index: 542

Text #3

Max Range: 0.9754. Min Range: -0.9754

Max Act: 0.8186. Min Act: -0.0000

Data Index: 1291340 (The Pile)

Max Activating Token Index: 515

Text #4

Max Range: 0.9754. Min Range: -0.9754

Max Act: 0.8875. Min Act: -0.0000

Data Index: 653988 (The Pile)

Max Activating Token Index: 884

Text #5

Max Range: 0.9754. Min Range: -0.9754

Max Act: 0.8373. Min Act: -0.0000

Data Index: 51667 (The Pile)

Max Activating Token Index: 365

Text #6

Max Range: 0.9754. Min Range: -0.9754

Max Act: 0.8412. Min Act: -0.0000

Data Index: 1720246 (The Pile)

Max Activating Token Index: 206

Text #7

Max Range: 0.9754. Min Range: -0.9754

Max Act: 0.8377. Min Act: -0.0000

Data Index: 19383 (The Pile)

Max Activating Token Index: 769

Text #8

Max Range: 0.9754. Min Range: -0.9754

Max Act: 0.8447. Min Act: -0.0000

Data Index: 886279 (The Pile)

Max Activating Token Index: 424

Text #9

Max Range: 0.9754. Min Range: -0.9754

Max Act: 0.9012. Min Act: -0.0000

Data Index: 1321370 (The Pile)

Max Activating Token Index: 45

Text #10

Max Range: 0.9754. Min Range: -0.9754

Max Act: 0.8426. Min Act: -0.0000

Data Index: 1730036 (The Pile)

Max Activating Token Index: 792

Text #11

Max Range: 0.9754. Min Range: -0.9754

Max Act: 0.7810. Min Act: -0.0000

Data Index: 629386 (The Pile)

Max Activating Token Index: 443

Text #12

Max Range: 0.9754. Min Range: -0.9754

Max Act: 0.8267. Min Act: -0.0000

Data Index: 1955543 (The Pile)

Max Activating Token Index: 819

Text #13

Max Range: 0.9754. Min Range: -0.9754

Max Act: 0.8276. Min Act: -0.0000

Data Index: 1255260 (The Pile)

Max Activating Token Index: 406

Text #14

Max Range: 0.9754. Min Range: -0.9754

Max Act: 0.7930. Min Act: -0.0000

Data Index: 730607 (The Pile)

Max Activating Token Index: 20

Text #15

Max Range: 0.9754. Min Range: -0.9754

Max Act: 0.7775. Min Act: -0.0000

Data Index: 1758977 (The Pile)

Max Activating Token Index: 239

Text #16

Max Range: 0.9754. Min Range: -0.9754

Max Act: 0.7992. Min Act: -0.0000

Data Index: 1816616 (The Pile)

Max Activating Token Index: 226

Text #17

Max Range: 0.9754. Min Range: -0.9754

Max Act: 0.8117. Min Act: -0.0000

Data Index: 1522664 (The Pile)

Max Activating Token Index: 231

Text #18

Max Range: 0.9754. Min Range: -0.9754

Max Act: 0.7670. Min Act: -0.0000

Data Index: 1911434 (The Pile)

Max Activating Token Index: 597

Text #19

Max Range: 0.9754. Min Range: -0.9754

Max Act: 0.7208. Min Act: -0.0000

Data Index: 307002 (The Pile)

Max Activating Token Index: 781