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

Dataset: The Pile

Neuron 4242 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: 1.3709. Min Range: -1.3709

Max Act: 1.3709. Min Act: -0.0000

Data Index: 237922 (The Pile)

Max Activating Token Index: 515

Text #1

Max Range: 1.3709. Min Range: -1.3709

Max Act: 1.2090. Min Act: -0.0000

Data Index: 68092 (The Pile)

Max Activating Token Index: 293

Text #2

Max Range: 1.3709. Min Range: -1.3709

Max Act: 1.0814. Min Act: -0.0000

Data Index: 1061993 (The Pile)

Max Activating Token Index: 114

Text #3

Max Range: 1.3709. Min Range: -1.3709

Max Act: 1.0775. Min Act: -0.0000

Data Index: 854747 (The Pile)

Max Activating Token Index: 237

Text #4

Max Range: 1.3709. Min Range: -1.3709

Max Act: 1.2077. Min Act: -0.0000

Data Index: 256241 (The Pile)

Max Activating Token Index: 753

Text #5

Max Range: 1.3709. Min Range: -1.3709

Max Act: 1.0295. Min Act: -0.0000

Data Index: 1371704 (The Pile)

Max Activating Token Index: 573

Text #6

Max Range: 1.3709. Min Range: -1.3709

Max Act: 1.0515. Min Act: -0.0000

Data Index: 203743 (The Pile)

Max Activating Token Index: 592

Text #7

Max Range: 1.3709. Min Range: -1.3709

Max Act: 1.0001. Min Act: -0.0000

Data Index: 807190 (The Pile)

Max Activating Token Index: 634

Text #8

Max Range: 1.3709. Min Range: -1.3709

Max Act: 1.0266. Min Act: -0.0000

Data Index: 1259917 (The Pile)

Max Activating Token Index: 888

Text #9

Max Range: 1.3709. Min Range: -1.3709

Max Act: 0.9862. Min Act: -0.0000

Data Index: 1195442 (The Pile)

Max Activating Token Index: 713

Text #10

Max Range: 1.3709. Min Range: -1.3709

Max Act: 0.9404. Min Act: -0.0000

Data Index: 1858962 (The Pile)

Max Activating Token Index: 450

Text #11

Max Range: 1.3709. Min Range: -1.3709

Max Act: 0.8867. Min Act: -0.0000

Data Index: 770034 (The Pile)

Max Activating Token Index: 960

Text #12

Max Range: 1.3709. Min Range: -1.3709

Max Act: 1.0012. Min Act: -0.0000

Data Index: 438759 (The Pile)

Max Activating Token Index: 989

Text #13

Max Range: 1.3709. Min Range: -1.3709

Max Act: 0.9906. Min Act: -0.0000

Data Index: 177385 (The Pile)

Max Activating Token Index: 639

Text #14

Max Range: 1.3709. Min Range: -1.3709

Max Act: 0.8929. Min Act: -0.0000

Data Index: 99723 (The Pile)

Max Activating Token Index: 267

Text #15

Max Range: 1.3709. Min Range: -1.3709

Max Act: 0.9919. Min Act: -0.0000

Data Index: 1759993 (The Pile)

Max Activating Token Index: 555

Text #16

Max Range: 1.3709. Min Range: -1.3709

Max Act: 0.9356. Min Act: -0.0000

Data Index: 1602429 (The Pile)

Max Activating Token Index: 486

Text #17

Max Range: 1.3709. Min Range: -1.3709

Max Act: 0.8391. Min Act: -0.0000

Data Index: 365306 (The Pile)

Max Activating Token Index: 540

Text #18

Max Range: 1.3709. Min Range: -1.3709

Max Act: 0.8627. Min Act: -0.0000

Data Index: 416291 (The Pile)

Max Activating Token Index: 593

Text #19

Max Range: 1.3709. Min Range: -1.3709

Max Act: 0.9781. Min Act: -0.0000

Data Index: 573926 (The Pile)

Max Activating Token Index: 783