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

Dataset: The Pile

Neuron 3789 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8958. Min Range: -0.8958

Max Act: 0.8958. Min Act: -0.0000

Data Index: 700485 (The Pile)

Max Activating Token Index: 749

Text #1

Max Range: 0.8958. Min Range: -0.8958

Max Act: 0.8590. Min Act: -0.0000

Data Index: 1848039 (The Pile)

Max Activating Token Index: 435

Text #2

Max Range: 0.8958. Min Range: -0.8958

Max Act: 0.8121. Min Act: -0.0000

Data Index: 1015053 (The Pile)

Max Activating Token Index: 122

Text #3

Max Range: 0.8958. Min Range: -0.8958

Max Act: 0.7568. Min Act: -0.0000

Data Index: 1902351 (The Pile)

Max Activating Token Index: 220

Text #4

Max Range: 0.8958. Min Range: -0.8958

Max Act: 0.7573. Min Act: -0.0000

Data Index: 511535 (The Pile)

Max Activating Token Index: 514

Text #5

Max Range: 0.8958. Min Range: -0.8958

Max Act: 0.7702. Min Act: 0.0000

Data Index: 919886 (The Pile)

Max Activating Token Index: 482

Text #6

Max Range: 0.8958. Min Range: -0.8958

Max Act: 0.8183. Min Act: -0.0000

Data Index: 26295 (The Pile)

Max Activating Token Index: 265

Text #7

Max Range: 0.8958. Min Range: -0.8958

Max Act: 0.7836. Min Act: -0.0000

Data Index: 443624 (The Pile)

Max Activating Token Index: 194

Text #8

Max Range: 0.8958. Min Range: -0.8958

Max Act: 0.6131. Min Act: -0.0000

Data Index: 1560111 (The Pile)

Max Activating Token Index: 990

Text #9

Max Range: 0.8958. Min Range: -0.8958

Max Act: 0.7200. Min Act: -0.0000

Data Index: 1331601 (The Pile)

Max Activating Token Index: 915

Text #10

Max Range: 0.8958. Min Range: -0.8958

Max Act: 0.7549. Min Act: -0.0000

Data Index: 809843 (The Pile)

Max Activating Token Index: 930

Text #11

Max Range: 0.8958. Min Range: -0.8958

Max Act: 0.7076. Min Act: -0.0000

Data Index: 521891 (The Pile)

Max Activating Token Index: 45

Text #12

Max Range: 0.8958. Min Range: -0.8958

Max Act: 0.6881. Min Act: 0.0000

Data Index: 1578063 (The Pile)

Max Activating Token Index: 220

Text #13

Max Range: 0.8958. Min Range: -0.8958

Max Act: 0.7032. Min Act: -0.0000

Data Index: 1959372 (The Pile)

Max Activating Token Index: 369

Text #14

Max Range: 0.8958. Min Range: -0.8958

Max Act: 0.6950. Min Act: 0.0000

Data Index: 432664 (The Pile)

Max Activating Token Index: 518

Text #15

Max Range: 0.8958. Min Range: -0.8958

Max Act: 0.7397. Min Act: -0.0000

Data Index: 1887242 (The Pile)

Max Activating Token Index: 666

Text #16

Max Range: 0.8958. Min Range: -0.8958

Max Act: 0.6309. Min Act: 0.0000

Data Index: 1281870 (The Pile)

Max Activating Token Index: 535

Text #17

Max Range: 0.8958. Min Range: -0.8958

Max Act: 0.6496. Min Act: -0.0000

Data Index: 683915 (The Pile)

Max Activating Token Index: 165

Text #18

Max Range: 0.8958. Min Range: -0.8958

Max Act: 0.6880. Min Act: -0.0000

Data Index: 343198 (The Pile)

Max Activating Token Index: 512

Text #19

Max Range: 0.8958. Min Range: -0.8958

Max Act: 0.6599. Min Act: -0.0000

Data Index: 997703 (The Pile)

Max Activating Token Index: 440