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

Dataset: The Pile

Neuron 2380 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: 0.8778. Min Range: -0.8778

Max Act: 0.8778. Min Act: -0.0000

Data Index: 1255256 (The Pile)

Max Activating Token Index: 329

Text #1

Max Range: 0.8778. Min Range: -0.8778

Max Act: 0.7615. Min Act: -0.0000

Data Index: 346401 (The Pile)

Max Activating Token Index: 976

Text #2

Max Range: 0.8778. Min Range: -0.8778

Max Act: 0.7267. Min Act: -0.0000

Data Index: 1149558 (The Pile)

Max Activating Token Index: 438

Text #3

Max Range: 0.8778. Min Range: -0.8778

Max Act: 0.5735. Min Act: -0.0000

Data Index: 555712 (The Pile)

Max Activating Token Index: 877

Text #4

Max Range: 0.8778. Min Range: -0.8778

Max Act: 0.5768. Min Act: -0.0000

Data Index: 112374 (The Pile)

Max Activating Token Index: 900

Text #5

Max Range: 0.8778. Min Range: -0.8778

Max Act: 0.5708. Min Act: -0.0000

Data Index: 1799743 (The Pile)

Max Activating Token Index: 1011

Text #6

Max Range: 0.8778. Min Range: -0.8778

Max Act: 0.5726. Min Act: -0.0000

Data Index: 1025646 (The Pile)

Max Activating Token Index: 265

Text #7

Max Range: 0.8778. Min Range: -0.8778

Max Act: 0.5343. Min Act: -0.0000

Data Index: 1639516 (The Pile)

Max Activating Token Index: 955

Text #8

Max Range: 0.8778. Min Range: -0.8778

Max Act: 0.5344. Min Act: -0.0000

Data Index: 569129 (The Pile)

Max Activating Token Index: 788

Text #9

Max Range: 0.8778. Min Range: -0.8778

Max Act: 0.5058. Min Act: -0.0000

Data Index: 1856839 (The Pile)

Max Activating Token Index: 927

Text #10

Max Range: 0.8778. Min Range: -0.8778

Max Act: 0.5147. Min Act: -0.0000

Data Index: 563465 (The Pile)

Max Activating Token Index: 221

Text #11

Max Range: 0.8778. Min Range: -0.8778

Max Act: 0.4492. Min Act: -0.0000

Data Index: 1837714 (The Pile)

Max Activating Token Index: 605

Text #12

Max Range: 0.8778. Min Range: -0.8778

Max Act: 0.4220. Min Act: -0.0000

Data Index: 870671 (The Pile)

Max Activating Token Index: 876

Text #13

Max Range: 0.8778. Min Range: -0.8778

Max Act: 0.4393. Min Act: -0.0000

Data Index: 770873 (The Pile)

Max Activating Token Index: 828

Text #14

Max Range: 0.8778. Min Range: -0.8778

Max Act: 0.4529. Min Act: -0.0000

Data Index: 1624321 (The Pile)

Max Activating Token Index: 563

Text #15

Max Range: 0.8778. Min Range: -0.8778

Max Act: 0.3989. Min Act: -0.0000

Data Index: 1773135 (The Pile)

Max Activating Token Index: 724

Text #16

Max Range: 0.8778. Min Range: -0.8778

Max Act: 0.4261. Min Act: -0.0000

Data Index: 201571 (The Pile)

Max Activating Token Index: 546

Text #17

Max Range: 0.8778. Min Range: -0.8778

Max Act: 0.4432. Min Act: -0.0000

Data Index: 316168 (The Pile)

Max Activating Token Index: 895

Text #18

Max Range: 0.8778. Min Range: -0.8778

Max Act: 0.4138. Min Act: -0.0000

Data Index: 22911 (The Pile)

Max Activating Token Index: 556

Text #19

Max Range: 0.8778. Min Range: -0.8778

Max Act: 0.4129. Min Act: -0.0000

Data Index: 990046 (The Pile)

Max Activating Token Index: 971