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

Dataset: The Pile

Neuron 2607 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0765. Min Range: -1.0765

Max Act: 1.0765. Min Act: -0.0000

Data Index: 468963 (The Pile)

Max Activating Token Index: 821

Text #1

Max Range: 1.0765. Min Range: -1.0765

Max Act: 0.7472. Min Act: -0.0000

Data Index: 604641 (The Pile)

Max Activating Token Index: 733

Text #2

Max Range: 1.0765. Min Range: -1.0765

Max Act: 0.7876. Min Act: -0.0000

Data Index: 1432709 (The Pile)

Max Activating Token Index: 262

Text #3

Max Range: 1.0765. Min Range: -1.0765

Max Act: 0.7529. Min Act: -0.0000

Data Index: 1160990 (The Pile)

Max Activating Token Index: 687

Text #4

Max Range: 1.0765. Min Range: -1.0765

Max Act: 0.7239. Min Act: -0.0000

Data Index: 1574020 (The Pile)

Max Activating Token Index: 422

Text #5

Max Range: 1.0765. Min Range: -1.0765

Max Act: 0.7786. Min Act: -0.0000

Data Index: 750434 (The Pile)

Max Activating Token Index: 67

Text #6

Max Range: 1.0765. Min Range: -1.0765

Max Act: 0.6840. Min Act: -0.0000

Data Index: 375369 (The Pile)

Max Activating Token Index: 772

Text #7

Max Range: 1.0765. Min Range: -1.0765

Max Act: 0.7096. Min Act: -0.0000

Data Index: 783124 (The Pile)

Max Activating Token Index: 332

Text #8

Max Range: 1.0765. Min Range: -1.0765

Max Act: 0.6541. Min Act: -0.0000

Data Index: 128708 (The Pile)

Max Activating Token Index: 51

Text #9

Max Range: 1.0765. Min Range: -1.0765

Max Act: 0.6624. Min Act: -0.0000

Data Index: 1612939 (The Pile)

Max Activating Token Index: 842

Text #10

Max Range: 1.0765. Min Range: -1.0765

Max Act: 0.6673. Min Act: -0.0000

Data Index: 1043701 (The Pile)

Max Activating Token Index: 51

Text #11

Max Range: 1.0765. Min Range: -1.0765

Max Act: 0.6969. Min Act: -0.0000

Data Index: 1838163 (The Pile)

Max Activating Token Index: 65

Text #12

Max Range: 1.0765. Min Range: -1.0765

Max Act: 0.6524. Min Act: -0.0000

Data Index: 441043 (The Pile)

Max Activating Token Index: 56

Text #13

Max Range: 1.0765. Min Range: -1.0765

Max Act: 0.6198. Min Act: 0.0000

Data Index: 256378 (The Pile)

Max Activating Token Index: 932

Text #14

Max Range: 1.0765. Min Range: -1.0765

Max Act: 0.6488. Min Act: -0.0000

Data Index: 900129 (The Pile)

Max Activating Token Index: 724

Text #15

Max Range: 1.0765. Min Range: -1.0765

Max Act: 0.5963. Min Act: 0.0001

Data Index: 1116638 (The Pile)

Max Activating Token Index: 621

Text #16

Max Range: 1.0765. Min Range: -1.0765

Max Act: 0.6066. Min Act: -0.0000

Data Index: 890531 (The Pile)

Max Activating Token Index: 184

Text #17

Max Range: 1.0765. Min Range: -1.0765

Max Act: 0.6159. Min Act: -0.0000

Data Index: 1321833 (The Pile)

Max Activating Token Index: 60

Text #18

Max Range: 1.0765. Min Range: -1.0765

Max Act: 0.6501. Min Act: -0.0000

Data Index: 1627475 (The Pile)

Max Activating Token Index: 811

Text #19

Max Range: 1.0765. Min Range: -1.0765

Max Act: 0.6106. Min Act: -0.0000

Data Index: 1561427 (The Pile)

Max Activating Token Index: 229