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

Dataset: The Pile

Neuron 1750 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: 1.9869. Min Range: -1.9869

Max Act: 1.9869. Min Act: -0.0000

Data Index: 691507 (The Pile)

Max Activating Token Index: 906

Text #1

Max Range: 1.9869. Min Range: -1.9869

Max Act: 1.6614. Min Act: -0.0000

Data Index: 1608477 (The Pile)

Max Activating Token Index: 852

Text #2

Max Range: 1.9869. Min Range: -1.9869

Max Act: 1.6532. Min Act: 0.0000

Data Index: 1453116 (The Pile)

Max Activating Token Index: 502

Text #3

Max Range: 1.9869. Min Range: -1.9869

Max Act: 1.3449. Min Act: -0.0000

Data Index: 998679 (The Pile)

Max Activating Token Index: 711

Text #4

Max Range: 1.9869. Min Range: -1.9869

Max Act: 1.3061. Min Act: -0.0000

Data Index: 842273 (The Pile)

Max Activating Token Index: 525

Text #5

Max Range: 1.9869. Min Range: -1.9869

Max Act: 1.3215. Min Act: 0.0000

Data Index: 1388375 (The Pile)

Max Activating Token Index: 898

Text #6

Max Range: 1.9869. Min Range: -1.9869

Max Act: 1.3154. Min Act: -0.0000

Data Index: 871473 (The Pile)

Max Activating Token Index: 434

Text #7

Max Range: 1.9869. Min Range: -1.9869

Max Act: 1.2138. Min Act: -0.0000

Data Index: 1306504 (The Pile)

Max Activating Token Index: 392

Text #8

Max Range: 1.9869. Min Range: -1.9869

Max Act: 1.2492. Min Act: 0.0000

Data Index: 463979 (The Pile)

Max Activating Token Index: 581

Text #9

Max Range: 1.9869. Min Range: -1.9869

Max Act: 1.0844. Min Act: -0.0000

Data Index: 1141915 (The Pile)

Max Activating Token Index: 305

Text #10

Max Range: 1.9869. Min Range: -1.9869

Max Act: 1.1097. Min Act: -0.0000

Data Index: 158236 (The Pile)

Max Activating Token Index: 563

Text #11

Max Range: 1.9869. Min Range: -1.9869

Max Act: 1.1606. Min Act: -0.0000

Data Index: 991464 (The Pile)

Max Activating Token Index: 728

Text #12

Max Range: 1.9869. Min Range: -1.9869

Max Act: 1.0969. Min Act: -0.0000

Data Index: 971524 (The Pile)

Max Activating Token Index: 584

Text #13

Max Range: 1.9869. Min Range: -1.9869

Max Act: 1.0796. Min Act: -0.0000

Data Index: 139618 (The Pile)

Max Activating Token Index: 725

Text #14

Max Range: 1.9869. Min Range: -1.9869

Max Act: 1.0807. Min Act: -0.0000

Data Index: 1868501 (The Pile)

Max Activating Token Index: 440

Text #15

Max Range: 1.9869. Min Range: -1.9869

Max Act: 1.0036. Min Act: 0.0000

Data Index: 1178090 (The Pile)

Max Activating Token Index: 335

Text #16

Max Range: 1.9869. Min Range: -1.9869

Max Act: 1.0535. Min Act: -0.0000

Data Index: 523880 (The Pile)

Max Activating Token Index: 356

Text #17

Max Range: 1.9869. Min Range: -1.9869

Max Act: 1.0915. Min Act: -0.0000

Data Index: 241785 (The Pile)

Max Activating Token Index: 335

Text #18

Max Range: 1.9869. Min Range: -1.9869

Max Act: 1.0312. Min Act: -0.0000

Data Index: 1666624 (The Pile)

Max Activating Token Index: 488

Text #19

Max Range: 1.9869. Min Range: -1.9869

Max Act: 0.9633. Min Act: -0.0000

Data Index: 260763 (The Pile)

Max Activating Token Index: 638