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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1413 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9531. Min Range: -1.9531

Max Act: 1.9531. Min Act: -0.0000

Data Index: 1596631 (Python Code)

Max Activating Token Index: 886

Text #1

Max Range: 1.9531. Min Range: -1.9531

Max Act: 1.6369. Min Act: -0.0000

Data Index: 1628172 (Python Code)

Max Activating Token Index: 754

Text #2

Max Range: 1.9531. Min Range: -1.9531

Max Act: 1.8512. Min Act: -0.0000

Data Index: 1410424 (Python Code)

Max Activating Token Index: 819

Text #3

Max Range: 1.9531. Min Range: -1.9531

Max Act: 1.6989. Min Act: -0.0000

Data Index: 1478999 (Python Code)

Max Activating Token Index: 129

Text #4

Max Range: 1.9531. Min Range: -1.9531

Max Act: 1.7060. Min Act: -0.0000

Data Index: 1401338 (Python Code)

Max Activating Token Index: 815

Text #5

Max Range: 1.9531. Min Range: -1.9531

Max Act: 1.6942. Min Act: -0.0000

Data Index: 1520519 (Python Code)

Max Activating Token Index: 671

Text #6

Max Range: 1.9531. Min Range: -1.9531

Max Act: 1.6998. Min Act: -0.0000

Data Index: 1641208 (Python Code)

Max Activating Token Index: 806

Text #7

Max Range: 1.9531. Min Range: -1.9531

Max Act: 1.4396. Min Act: -0.0000

Data Index: 1377448 (Python Code)

Max Activating Token Index: 693

Text #8

Max Range: 1.9531. Min Range: -1.9531

Max Act: 1.6400. Min Act: -0.0000

Data Index: 1585191 (Python Code)

Max Activating Token Index: 945

Text #9

Max Range: 1.9531. Min Range: -1.9531

Max Act: 1.4683. Min Act: -0.0000

Data Index: 1550147 (Python Code)

Max Activating Token Index: 892

Text #10

Max Range: 1.9531. Min Range: -1.9531

Max Act: 1.5768. Min Act: -0.0000

Data Index: 1509127 (Python Code)

Max Activating Token Index: 906

Text #11

Max Range: 1.9531. Min Range: -1.9531

Max Act: 1.5062. Min Act: -0.0000

Data Index: 1474417 (Python Code)

Max Activating Token Index: 835

Text #12

Max Range: 1.9531. Min Range: -1.9531

Max Act: 1.5585. Min Act: -0.0000

Data Index: 1460990 (Python Code)

Max Activating Token Index: 959

Text #13

Max Range: 1.9531. Min Range: -1.9531

Max Act: 1.4834. Min Act: -0.0000

Data Index: 1596777 (Python Code)

Max Activating Token Index: 740

Text #14

Max Range: 1.9531. Min Range: -1.9531

Max Act: 1.4465. Min Act: -0.0000

Data Index: 1576334 (Python Code)

Max Activating Token Index: 657

Text #15

Max Range: 1.9531. Min Range: -1.9531

Max Act: 1.5069. Min Act: -0.0000

Data Index: 1388455 (Python Code)

Max Activating Token Index: 307

Text #16

Max Range: 1.9531. Min Range: -1.9531

Max Act: 1.3705. Min Act: -0.0000

Data Index: 1556119 (Python Code)

Max Activating Token Index: 631

Text #17

Max Range: 1.9531. Min Range: -1.9531

Max Act: 1.5332. Min Act: -0.0000

Data Index: 1653174 (Python Code)

Max Activating Token Index: 841

Text #18

Max Range: 1.9531. Min Range: -1.9531

Max Act: 1.4157. Min Act: -0.0000

Data Index: 1372526 (Python Code)

Max Activating Token Index: 1004

Text #19

Max Range: 1.9531. Min Range: -1.9531

Max Act: 1.3254. Min Act: -0.0000

Data Index: 1605463 (Python Code)

Max Activating Token Index: 516