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

Dataset: The Pile

Neuron 4583 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: 1.2051. Min Range: -1.2051

Max Act: 1.2051. Min Act: -0.0000

Data Index: 514402 (The Pile)

Max Activating Token Index: 860

Text #1

Max Range: 1.2051. Min Range: -1.2051

Max Act: 0.8574. Min Act: -0.0000

Data Index: 987584 (The Pile)

Max Activating Token Index: 63

Text #2

Max Range: 1.2051. Min Range: -1.2051

Max Act: 0.8285. Min Act: -0.0000

Data Index: 127460 (The Pile)

Max Activating Token Index: 959

Text #3

Max Range: 1.2051. Min Range: -1.2051

Max Act: 0.7906. Min Act: -0.0000

Data Index: 1452778 (The Pile)

Max Activating Token Index: 311

Text #4

Max Range: 1.2051. Min Range: -1.2051

Max Act: 0.7814. Min Act: -0.0000

Data Index: 642193 (The Pile)

Max Activating Token Index: 991

Text #5

Max Range: 1.2051. Min Range: -1.2051

Max Act: 0.7821. Min Act: -0.0000

Data Index: 700487 (The Pile)

Max Activating Token Index: 530

Text #6

Max Range: 1.2051. Min Range: -1.2051

Max Act: 0.7727. Min Act: -0.0000

Data Index: 279057 (The Pile)

Max Activating Token Index: 699

Text #7

Max Range: 1.2051. Min Range: -1.2051

Max Act: 0.7157. Min Act: -0.0000

Data Index: 1435134 (The Pile)

Max Activating Token Index: 495

Text #8

Max Range: 1.2051. Min Range: -1.2051

Max Act: 0.8379. Min Act: -0.0000

Data Index: 1699971 (The Pile)

Max Activating Token Index: 528

Text #9

Max Range: 1.2051. Min Range: -1.2051

Max Act: 0.7317. Min Act: -0.0000

Data Index: 82586 (The Pile)

Max Activating Token Index: 915

Text #10

Max Range: 1.2051. Min Range: -1.2051

Max Act: 0.7495. Min Act: -0.0000

Data Index: 450096 (The Pile)

Max Activating Token Index: 944

Text #11

Max Range: 1.2051. Min Range: -1.2051

Max Act: 0.7077. Min Act: -0.0000

Data Index: 1820417 (The Pile)

Max Activating Token Index: 916

Text #12

Max Range: 1.2051. Min Range: -1.2051

Max Act: 0.7147. Min Act: -0.0000

Data Index: 1064122 (The Pile)

Max Activating Token Index: 268

Text #13

Max Range: 1.2051. Min Range: -1.2051

Max Act: 0.7313. Min Act: -0.0000

Data Index: 974330 (The Pile)

Max Activating Token Index: 288

Text #14

Max Range: 1.2051. Min Range: -1.2051

Max Act: 0.7063. Min Act: -0.0000

Data Index: 1924206 (The Pile)

Max Activating Token Index: 251

Text #15

Max Range: 1.2051. Min Range: -1.2051

Max Act: 0.6557. Min Act: -0.0000

Data Index: 1917037 (The Pile)

Max Activating Token Index: 818

Text #16

Max Range: 1.2051. Min Range: -1.2051

Max Act: 0.7216. Min Act: -0.0000

Data Index: 1318769 (The Pile)

Max Activating Token Index: 392

Text #17

Max Range: 1.2051. Min Range: -1.2051

Max Act: 0.6631. Min Act: -0.0000

Data Index: 551248 (The Pile)

Max Activating Token Index: 463

Text #18

Max Range: 1.2051. Min Range: -1.2051

Max Act: 0.7332. Min Act: -0.0000

Data Index: 694399 (The Pile)

Max Activating Token Index: 597

Text #19

Max Range: 1.2051. Min Range: -1.2051

Max Act: 0.7828. Min Act: -0.0000

Data Index: 654611 (The Pile)

Max Activating Token Index: 682