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

Dataset: The Pile

Neuron 4104 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4559. Min Range: -1.4559

Max Act: 1.4559. Min Act: -0.0000

Data Index: 1496899 (The Pile)

Max Activating Token Index: 94

Text #1

Max Range: 1.4559. Min Range: -1.4559

Max Act: 1.3256. Min Act: -0.0000

Data Index: 1994245 (The Pile)

Max Activating Token Index: 739

Text #2

Max Range: 1.4559. Min Range: -1.4559

Max Act: 1.2814. Min Act: -0.0000

Data Index: 1115068 (The Pile)

Max Activating Token Index: 683

Text #3

Max Range: 1.4559. Min Range: -1.4559

Max Act: 1.2000. Min Act: -0.0000

Data Index: 1038409 (The Pile)

Max Activating Token Index: 498

Text #4

Max Range: 1.4559. Min Range: -1.4559

Max Act: 1.1680. Min Act: -0.0000

Data Index: 1728773 (The Pile)

Max Activating Token Index: 320

Text #5

Max Range: 1.4559. Min Range: -1.4559

Max Act: 1.2250. Min Act: -0.0000

Data Index: 800351 (The Pile)

Max Activating Token Index: 483

Text #6

Max Range: 1.4559. Min Range: -1.4559

Max Act: 0.9929. Min Act: -0.0000

Data Index: 1736052 (The Pile)

Max Activating Token Index: 999

Text #7

Max Range: 1.4559. Min Range: -1.4559

Max Act: 1.0408. Min Act: -0.0000

Data Index: 1978823 (The Pile)

Max Activating Token Index: 991

Text #8

Max Range: 1.4559. Min Range: -1.4559

Max Act: 0.9871. Min Act: -0.0000

Data Index: 1933759 (The Pile)

Max Activating Token Index: 325

Text #9

Max Range: 1.4559. Min Range: -1.4559

Max Act: 0.9837. Min Act: -0.0000

Data Index: 324067 (The Pile)

Max Activating Token Index: 94

Text #10

Max Range: 1.4559. Min Range: -1.4559

Max Act: 0.9136. Min Act: -0.0000

Data Index: 1300341 (The Pile)

Max Activating Token Index: 274

Text #11

Max Range: 1.4559. Min Range: -1.4559

Max Act: 0.9265. Min Act: -0.0000

Data Index: 501169 (The Pile)

Max Activating Token Index: 807

Text #12

Max Range: 1.4559. Min Range: -1.4559

Max Act: 0.9424. Min Act: -0.0000

Data Index: 828919 (The Pile)

Max Activating Token Index: 433

Text #13

Max Range: 1.4559. Min Range: -1.4559

Max Act: 0.9371. Min Act: -0.0000

Data Index: 1821990 (The Pile)

Max Activating Token Index: 206

Text #14

Max Range: 1.4559. Min Range: -1.4559

Max Act: 0.9158. Min Act: -0.0000

Data Index: 117611 (The Pile)

Max Activating Token Index: 381

Text #15

Max Range: 1.4559. Min Range: -1.4559

Max Act: 0.9396. Min Act: -0.0000

Data Index: 144162 (The Pile)

Max Activating Token Index: 87

Text #16

Max Range: 1.4559. Min Range: -1.4559

Max Act: 0.9597. Min Act: -0.0000

Data Index: 1412596 (The Pile)

Max Activating Token Index: 24

Text #17

Max Range: 1.4559. Min Range: -1.4559

Max Act: 0.9266. Min Act: -0.0000

Data Index: 705125 (The Pile)

Max Activating Token Index: 299

Text #18

Max Range: 1.4559. Min Range: -1.4559

Max Act: 0.9504. Min Act: -0.0000

Data Index: 1998638 (The Pile)

Max Activating Token Index: 70

Text #19

Max Range: 1.4559. Min Range: -1.4559

Max Act: 0.9003. Min Act: -0.0000

Data Index: 994679 (The Pile)

Max Activating Token Index: 563