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

Dataset: The Pile

Neuron 970 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8955. Min Range: -0.8955

Max Act: 0.8955. Min Act: -0.0000

Data Index: 875847 (The Pile)

Max Activating Token Index: 441

Text #1

Max Range: 0.8955. Min Range: -0.8955

Max Act: 0.7643. Min Act: -0.0000

Data Index: 695103 (The Pile)

Max Activating Token Index: 246

Text #2

Max Range: 0.8955. Min Range: -0.8955

Max Act: 0.7767. Min Act: -0.0000

Data Index: 130312 (The Pile)

Max Activating Token Index: 184

Text #3

Max Range: 0.8955. Min Range: -0.8955

Max Act: 0.8020. Min Act: -0.0000

Data Index: 1387511 (The Pile)

Max Activating Token Index: 981

Text #4

Max Range: 0.8955. Min Range: -0.8955

Max Act: 0.7119. Min Act: -0.0000

Data Index: 921368 (The Pile)

Max Activating Token Index: 442

Text #5

Max Range: 0.8955. Min Range: -0.8955

Max Act: 0.7692. Min Act: -0.0000

Data Index: 1188675 (The Pile)

Max Activating Token Index: 388

Text #6

Max Range: 0.8955. Min Range: -0.8955

Max Act: 0.7321. Min Act: -0.0000

Data Index: 1001303 (The Pile)

Max Activating Token Index: 105

Text #7

Max Range: 0.8955. Min Range: -0.8955

Max Act: 0.6917. Min Act: -0.0000

Data Index: 690651 (The Pile)

Max Activating Token Index: 584

Text #8

Max Range: 0.8955. Min Range: -0.8955

Max Act: 0.6674. Min Act: -0.0000

Data Index: 1047309 (The Pile)

Max Activating Token Index: 504

Text #9

Max Range: 0.8955. Min Range: -0.8955

Max Act: 0.7157. Min Act: -0.0000

Data Index: 1854381 (The Pile)

Max Activating Token Index: 486

Text #10

Max Range: 0.8955. Min Range: -0.8955

Max Act: 0.6945. Min Act: -0.0000

Data Index: 884632 (The Pile)

Max Activating Token Index: 259

Text #11

Max Range: 0.8955. Min Range: -0.8955

Max Act: 0.6650. Min Act: -0.0000

Data Index: 1854172 (The Pile)

Max Activating Token Index: 405

Text #12

Max Range: 0.8955. Min Range: -0.8955

Max Act: 0.6606. Min Act: -0.0000

Data Index: 895372 (The Pile)

Max Activating Token Index: 179

Text #13

Max Range: 0.8955. Min Range: -0.8955

Max Act: 0.6361. Min Act: -0.0000

Data Index: 1785980 (The Pile)

Max Activating Token Index: 643

Text #14

Max Range: 0.8955. Min Range: -0.8955

Max Act: 0.6925. Min Act: -0.0000

Data Index: 815055 (The Pile)

Max Activating Token Index: 673

Text #15

Max Range: 0.8955. Min Range: -0.8955

Max Act: 0.6912. Min Act: -0.0000

Data Index: 1457277 (The Pile)

Max Activating Token Index: 476

Text #16

Max Range: 0.8955. Min Range: -0.8955

Max Act: 0.6298. Min Act: -0.0000

Data Index: 677108 (The Pile)

Max Activating Token Index: 733

Text #17

Max Range: 0.8955. Min Range: -0.8955

Max Act: 0.6867. Min Act: -0.0000

Data Index: 973291 (The Pile)

Max Activating Token Index: 432

Text #18

Max Range: 0.8955. Min Range: -0.8955

Max Act: 0.6686. Min Act: -0.0000

Data Index: 1488134 (The Pile)

Max Activating Token Index: 244

Text #19

Max Range: 0.8955. Min Range: -0.8955

Max Act: 0.6850. Min Act: -0.0000

Data Index: 744221 (The Pile)

Max Activating Token Index: 418