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

Dataset: The Pile

Neuron 2159 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1511. Min Range: -1.1511

Max Act: 1.0593. Min Act: -0.0000

Data Index: 1414261 (The Pile)

Max Activating Token Index: 470

Text #1

Max Range: 1.1511. Min Range: -1.1511

Max Act: 1.1511. Min Act: -0.0000

Data Index: 1603975 (The Pile)

Max Activating Token Index: 632

Text #2

Max Range: 1.1511. Min Range: -1.1511

Max Act: 0.9339. Min Act: -0.0000

Data Index: 1305146 (The Pile)

Max Activating Token Index: 587

Text #3

Max Range: 1.1511. Min Range: -1.1511

Max Act: 0.8719. Min Act: -0.0000

Data Index: 489017 (The Pile)

Max Activating Token Index: 905

Text #4

Max Range: 1.1511. Min Range: -1.1511

Max Act: 0.8767. Min Act: -0.0000

Data Index: 1468652 (The Pile)

Max Activating Token Index: 554

Text #5

Max Range: 1.1511. Min Range: -1.1511

Max Act: 0.9261. Min Act: -0.0000

Data Index: 1907709 (The Pile)

Max Activating Token Index: 462

Text #6

Max Range: 1.1511. Min Range: -1.1511

Max Act: 0.9249. Min Act: -0.0000

Data Index: 1563891 (The Pile)

Max Activating Token Index: 666

Text #7

Max Range: 1.1511. Min Range: -1.1511

Max Act: 0.8312. Min Act: -0.0000

Data Index: 1052921 (The Pile)

Max Activating Token Index: 906

Text #8

Max Range: 1.1511. Min Range: -1.1511

Max Act: 0.8418. Min Act: -0.0000

Data Index: 353937 (The Pile)

Max Activating Token Index: 877

Text #9

Max Range: 1.1511. Min Range: -1.1511

Max Act: 0.8785. Min Act: -0.0000

Data Index: 353060 (The Pile)

Max Activating Token Index: 589

Text #10

Max Range: 1.1511. Min Range: -1.1511

Max Act: 0.8804. Min Act: -0.0000

Data Index: 853668 (The Pile)

Max Activating Token Index: 418

Text #11

Max Range: 1.1511. Min Range: -1.1511

Max Act: 0.9536. Min Act: -0.0000

Data Index: 1450347 (The Pile)

Max Activating Token Index: 221

Text #12

Max Range: 1.1511. Min Range: -1.1511

Max Act: 0.8525. Min Act: -0.0000

Data Index: 1797117 (The Pile)

Max Activating Token Index: 42

Text #13

Max Range: 1.1511. Min Range: -1.1511

Max Act: 0.8672. Min Act: -0.0000

Data Index: 1374560 (The Pile)

Max Activating Token Index: 312

Text #14

Max Range: 1.1511. Min Range: -1.1511

Max Act: 0.8530. Min Act: -0.0000

Data Index: 1415795 (The Pile)

Max Activating Token Index: 486

Text #15

Max Range: 1.1511. Min Range: -1.1511

Max Act: 0.8771. Min Act: -0.0000

Data Index: 1020019 (The Pile)

Max Activating Token Index: 157

Text #16

Max Range: 1.1511. Min Range: -1.1511

Max Act: 0.8473. Min Act: -0.0000

Data Index: 1733903 (The Pile)

Max Activating Token Index: 290

Text #17

Max Range: 1.1511. Min Range: -1.1511

Max Act: 0.8459. Min Act: -0.0000

Data Index: 1392366 (The Pile)

Max Activating Token Index: 412

Text #18

Max Range: 1.1511. Min Range: -1.1511

Max Act: 0.8661. Min Act: -0.0000

Data Index: 1467883 (The Pile)

Max Activating Token Index: 529

Text #19

Max Range: 1.1511. Min Range: -1.1511

Max Act: 0.8294. Min Act: -0.0000

Data Index: 57074 (The Pile)

Max Activating Token Index: 882