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

Dataset: The Pile

Neuron 2033 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: 1.4903. Min Range: -1.4903

Max Act: 1.4903. Min Act: -0.0000

Data Index: 133596 (The Pile)

Max Activating Token Index: 507

Text #1

Max Range: 1.4903. Min Range: -1.4903

Max Act: 1.2298. Min Act: -0.0000

Data Index: 1412828 (The Pile)

Max Activating Token Index: 707

Text #2

Max Range: 1.4903. Min Range: -1.4903

Max Act: 1.2898. Min Act: -0.0000

Data Index: 664371 (The Pile)

Max Activating Token Index: 821

Text #3

Max Range: 1.4903. Min Range: -1.4903

Max Act: 1.1988. Min Act: -0.0000

Data Index: 1447535 (The Pile)

Max Activating Token Index: 791

Text #4

Max Range: 1.4903. Min Range: -1.4903

Max Act: 1.1533. Min Act: -0.0000

Data Index: 297813 (The Pile)

Max Activating Token Index: 418

Text #5

Max Range: 1.4903. Min Range: -1.4903

Max Act: 1.1651. Min Act: -0.0000

Data Index: 1208097 (The Pile)

Max Activating Token Index: 325

Text #6

Max Range: 1.4903. Min Range: -1.4903

Max Act: 1.1036. Min Act: -0.0000

Data Index: 1347540 (The Pile)

Max Activating Token Index: 104

Text #7

Max Range: 1.4903. Min Range: -1.4903

Max Act: 0.9612. Min Act: -0.0000

Data Index: 1378479 (The Pile)

Max Activating Token Index: 183

Text #8

Max Range: 1.4903. Min Range: -1.4903

Max Act: 1.0584. Min Act: -0.0000

Data Index: 696444 (The Pile)

Max Activating Token Index: 92

Text #9

Max Range: 1.4903. Min Range: -1.4903

Max Act: 0.9027. Min Act: -0.0000

Data Index: 50736 (The Pile)

Max Activating Token Index: 865

Text #10

Max Range: 1.4903. Min Range: -1.4903

Max Act: 0.8568. Min Act: -0.0000

Data Index: 1717551 (The Pile)

Max Activating Token Index: 187

Text #11

Max Range: 1.4903. Min Range: -1.4903

Max Act: 0.6965. Min Act: -0.0000

Data Index: 798548 (The Pile)

Max Activating Token Index: 125

Text #12

Max Range: 1.4903. Min Range: -1.4903

Max Act: 0.8296. Min Act: -0.0000

Data Index: 548352 (The Pile)

Max Activating Token Index: 143

Text #13

Max Range: 1.4903. Min Range: -1.4903

Max Act: 0.7715. Min Act: -0.0000

Data Index: 1736355 (The Pile)

Max Activating Token Index: 44

Text #14

Max Range: 1.4903. Min Range: -1.4903

Max Act: 0.7564. Min Act: -0.0000

Data Index: 643826 (The Pile)

Max Activating Token Index: 418

Text #15

Max Range: 1.4903. Min Range: -1.4903

Max Act: 0.6958. Min Act: -0.0000

Data Index: 471288 (The Pile)

Max Activating Token Index: 555

Text #16

Max Range: 1.4903. Min Range: -1.4903

Max Act: 0.7578. Min Act: -0.0000

Data Index: 1923750 (The Pile)

Max Activating Token Index: 576

Text #17

Max Range: 1.4903. Min Range: -1.4903

Max Act: 0.7324. Min Act: -0.0000

Data Index: 1475674 (The Pile)

Max Activating Token Index: 249

Text #18

Max Range: 1.4903. Min Range: -1.4903

Max Act: 0.7287. Min Act: -0.0000

Data Index: 772856 (The Pile)

Max Activating Token Index: 414

Text #19

Max Range: 1.4903. Min Range: -1.4903

Max Act: 0.6761. Min Act: -0.0000

Data Index: 161651 (The Pile)

Max Activating Token Index: 283