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

Dataset: The Pile

Neuron 1305 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3044. Min Range: -1.3044

Max Act: 1.3044. Min Act: -0.0000

Data Index: 437558 (The Pile)

Max Activating Token Index: 417

Text #1

Max Range: 1.3044. Min Range: -1.3044

Max Act: 1.2117. Min Act: -0.0000

Data Index: 1143513 (The Pile)

Max Activating Token Index: 253

Text #2

Max Range: 1.3044. Min Range: -1.3044

Max Act: 1.0777. Min Act: -0.0000

Data Index: 999902 (The Pile)

Max Activating Token Index: 458

Text #3

Max Range: 1.3044. Min Range: -1.3044

Max Act: 1.0714. Min Act: -0.0000

Data Index: 1573877 (The Pile)

Max Activating Token Index: 403

Text #4

Max Range: 1.3044. Min Range: -1.3044

Max Act: 0.9835. Min Act: -0.0000

Data Index: 1103548 (The Pile)

Max Activating Token Index: 511

Text #5

Max Range: 1.3044. Min Range: -1.3044

Max Act: 0.9326. Min Act: -0.0000

Data Index: 1137016 (The Pile)

Max Activating Token Index: 904

Text #6

Max Range: 1.3044. Min Range: -1.3044

Max Act: 1.0055. Min Act: -0.0000

Data Index: 554757 (The Pile)

Max Activating Token Index: 565

Text #7

Max Range: 1.3044. Min Range: -1.3044

Max Act: 0.9266. Min Act: -0.0000

Data Index: 1423453 (The Pile)

Max Activating Token Index: 822

Text #8

Max Range: 1.3044. Min Range: -1.3044

Max Act: 1.0263. Min Act: -0.0000

Data Index: 1826528 (The Pile)

Max Activating Token Index: 775

Text #9

Max Range: 1.3044. Min Range: -1.3044

Max Act: 0.9832. Min Act: -0.0000

Data Index: 330764 (The Pile)

Max Activating Token Index: 484

Text #10

Max Range: 1.3044. Min Range: -1.3044

Max Act: 1.0524. Min Act: -0.0000

Data Index: 1040683 (The Pile)

Max Activating Token Index: 71

Text #11

Max Range: 1.3044. Min Range: -1.3044

Max Act: 1.0602. Min Act: -0.0000

Data Index: 645996 (The Pile)

Max Activating Token Index: 581

Text #12

Max Range: 1.3044. Min Range: -1.3044

Max Act: 0.9343. Min Act: -0.0000

Data Index: 1333254 (The Pile)

Max Activating Token Index: 465

Text #13

Max Range: 1.3044. Min Range: -1.3044

Max Act: 0.8870. Min Act: -0.0000

Data Index: 915974 (The Pile)

Max Activating Token Index: 772

Text #14

Max Range: 1.3044. Min Range: -1.3044

Max Act: 0.9369. Min Act: -0.0000

Data Index: 1124948 (The Pile)

Max Activating Token Index: 499

Text #15

Max Range: 1.3044. Min Range: -1.3044

Max Act: 1.0315. Min Act: -0.0000

Data Index: 1781762 (The Pile)

Max Activating Token Index: 589

Text #16

Max Range: 1.3044. Min Range: -1.3044

Max Act: 0.9649. Min Act: -0.0000

Data Index: 13075 (The Pile)

Max Activating Token Index: 990

Text #17

Max Range: 1.3044. Min Range: -1.3044

Max Act: 0.9719. Min Act: -0.0000

Data Index: 1078867 (The Pile)

Max Activating Token Index: 764

Text #18

Max Range: 1.3044. Min Range: -1.3044

Max Act: 0.8767. Min Act: -0.0000

Data Index: 1014723 (The Pile)

Max Activating Token Index: 751

Text #19

Max Range: 1.3044. Min Range: -1.3044

Max Act: 0.9046. Min Act: -0.0000

Data Index: 704247 (The Pile)

Max Activating Token Index: 487