Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 515 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.4809. Min Range: -0.4809

Max Act: 0.4590. Min Act: -0.0000

Data Index: 1381503 (The Pile)

Max Activating Token Index: 391

Text #1

Max Range: 0.4809. Min Range: -0.4809

Max Act: 0.4288. Min Act: -0.0000

Data Index: 426758 (The Pile)

Max Activating Token Index: 116

Text #2

Max Range: 0.4809. Min Range: -0.4809

Max Act: 0.4202. Min Act: -0.0000

Data Index: 687367 (The Pile)

Max Activating Token Index: 69

Text #3

Max Range: 0.4809. Min Range: -0.4809

Max Act: 0.4606. Min Act: -0.0000

Data Index: 692921 (The Pile)

Max Activating Token Index: 767

Text #4

Max Range: 0.4809. Min Range: -0.4809

Max Act: 0.4580. Min Act: -0.0000

Data Index: 1784225 (The Pile)

Max Activating Token Index: 219

Text #5

Max Range: 0.4809. Min Range: -0.4809

Max Act: 0.4045. Min Act: -0.0000

Data Index: 1049379 (The Pile)

Max Activating Token Index: 604

Text #6

Max Range: 0.4809. Min Range: -0.4809

Max Act: 0.3702. Min Act: -0.0000

Data Index: 531418 (The Pile)

Max Activating Token Index: 661

Text #7

Max Range: 0.4809. Min Range: -0.4809

Max Act: 0.4809. Min Act: -0.0000

Data Index: 1025861 (The Pile)

Max Activating Token Index: 609

Text #8

Max Range: 0.4809. Min Range: -0.4809

Max Act: 0.3756. Min Act: -0.0000

Data Index: 389512 (The Pile)

Max Activating Token Index: 188

Text #9

Max Range: 0.4809. Min Range: -0.4809

Max Act: 0.4478. Min Act: -0.0000

Data Index: 867800 (The Pile)

Max Activating Token Index: 731

Text #10

Max Range: 0.4809. Min Range: -0.4809

Max Act: 0.3797. Min Act: -0.0000

Data Index: 49641 (The Pile)

Max Activating Token Index: 311

Text #11

Max Range: 0.4809. Min Range: -0.4809

Max Act: 0.3536. Min Act: -0.0000

Data Index: 1510956 (The Pile)

Max Activating Token Index: 264

Text #12

Max Range: 0.4809. Min Range: -0.4809

Max Act: 0.4237. Min Act: -0.0000

Data Index: 500754 (The Pile)

Max Activating Token Index: 392

Text #13

Max Range: 0.4809. Min Range: -0.4809

Max Act: 0.3813. Min Act: -0.0000

Data Index: 1832261 (The Pile)

Max Activating Token Index: 247

Text #14

Max Range: 0.4809. Min Range: -0.4809

Max Act: 0.3960. Min Act: -0.0000

Data Index: 1811435 (The Pile)

Max Activating Token Index: 925

Text #15

Max Range: 0.4809. Min Range: -0.4809

Max Act: 0.3345. Min Act: -0.0000

Data Index: 1764804 (The Pile)

Max Activating Token Index: 710

Text #16

Max Range: 0.4809. Min Range: -0.4809

Max Act: 0.3476. Min Act: -0.0000

Data Index: 1126636 (The Pile)

Max Activating Token Index: 831

Text #17

Max Range: 0.4809. Min Range: -0.4809

Max Act: 0.3020. Min Act: -0.0000

Data Index: 1476887 (The Pile)

Max Activating Token Index: 655

Text #18

Max Range: 0.4809. Min Range: -0.4809

Max Act: 0.3875. Min Act: -0.0000

Data Index: 335585 (The Pile)

Max Activating Token Index: 715

Text #19

Max Range: 0.4809. Min Range: -0.4809

Max Act: 0.4079. Min Act: -0.0000

Data Index: 235708 (The Pile)

Max Activating Token Index: 124