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

Dataset: The Pile

Neuron 327 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: 0.9841. Min Range: -0.9841

Max Act: 0.9841. Min Act: -0.0000

Data Index: 1923959 (The Pile)

Max Activating Token Index: 16

Text #1

Max Range: 0.9841. Min Range: -0.9841

Max Act: 0.8170. Min Act: -0.0000

Data Index: 424502 (The Pile)

Max Activating Token Index: 998

Text #2

Max Range: 0.9841. Min Range: -0.9841

Max Act: 0.6736. Min Act: -0.0000

Data Index: 303015 (The Pile)

Max Activating Token Index: 603

Text #3

Max Range: 0.9841. Min Range: -0.9841

Max Act: 0.6270. Min Act: -0.0000

Data Index: 1231106 (The Pile)

Max Activating Token Index: 831

Text #4

Max Range: 0.9841. Min Range: -0.9841

Max Act: 0.6367. Min Act: -0.0000

Data Index: 1959174 (The Pile)

Max Activating Token Index: 639

Text #5

Max Range: 0.9841. Min Range: -0.9841

Max Act: 0.6079. Min Act: -0.0000

Data Index: 70390 (The Pile)

Max Activating Token Index: 651

Text #6

Max Range: 0.9841. Min Range: -0.9841

Max Act: 0.5802. Min Act: -0.0000

Data Index: 1321511 (The Pile)

Max Activating Token Index: 1000

Text #7

Max Range: 0.9841. Min Range: -0.9841

Max Act: 0.6145. Min Act: -0.0000

Data Index: 1635135 (The Pile)

Max Activating Token Index: 924

Text #8

Max Range: 0.9841. Min Range: -0.9841

Max Act: 0.5745. Min Act: -0.0000

Data Index: 1589903 (The Pile)

Max Activating Token Index: 470

Text #9

Max Range: 0.9841. Min Range: -0.9841

Max Act: 0.5629. Min Act: -0.0000

Data Index: 867324 (The Pile)

Max Activating Token Index: 334

Text #10

Max Range: 0.9841. Min Range: -0.9841

Max Act: 0.5722. Min Act: -0.0000

Data Index: 353060 (The Pile)

Max Activating Token Index: 1003

Text #11

Max Range: 0.9841. Min Range: -0.9841

Max Act: 0.5513. Min Act: -0.0000

Data Index: 1467883 (The Pile)

Max Activating Token Index: 943

Text #12

Max Range: 0.9841. Min Range: -0.9841

Max Act: 0.5817. Min Act: -0.0000

Data Index: 975123 (The Pile)

Max Activating Token Index: 681

Text #13

Max Range: 0.9841. Min Range: -0.9841

Max Act: 0.5531. Min Act: -0.0000

Data Index: 1907709 (The Pile)

Max Activating Token Index: 876

Text #14

Max Range: 0.9841. Min Range: -0.9841

Max Act: 0.5485. Min Act: -0.0000

Data Index: 189281 (The Pile)

Max Activating Token Index: 846

Text #15

Max Range: 0.9841. Min Range: -0.9841

Max Act: 0.5453. Min Act: -0.0000

Data Index: 1758345 (The Pile)

Max Activating Token Index: 241

Text #16

Max Range: 0.9841. Min Range: -0.9841

Max Act: 0.5278. Min Act: -0.0000

Data Index: 148953 (The Pile)

Max Activating Token Index: 922

Text #17

Max Range: 0.9841. Min Range: -0.9841

Max Act: 0.5873. Min Act: -0.0000

Data Index: 1716132 (The Pile)

Max Activating Token Index: 86

Text #18

Max Range: 0.9841. Min Range: -0.9841

Max Act: 0.5716. Min Act: -0.0000

Data Index: 1415795 (The Pile)

Max Activating Token Index: 409

Text #19

Max Range: 0.9841. Min Range: -0.9841

Max Act: 0.5381. Min Act: -0.0000

Data Index: 104433 (The Pile)

Max Activating Token Index: 873