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

Dataset: The Pile

Neuron 24 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3768. Min Range: -3.3768

Max Act: 3.2996. Min Act: -0.0000

Data Index: 573624 (The Pile)

Max Activating Token Index: 128

Text #1

Max Range: 3.3768. Min Range: -3.3768

Max Act: 3.0807. Min Act: -0.0000

Data Index: 887294 (The Pile)

Max Activating Token Index: 923

Text #2

Max Range: 3.3768. Min Range: -3.3768

Max Act: 2.9088. Min Act: -0.0000

Data Index: 575389 (The Pile)

Max Activating Token Index: 283

Text #3

Max Range: 3.3768. Min Range: -3.3768

Max Act: 3.3768. Min Act: -0.0000

Data Index: 115430 (The Pile)

Max Activating Token Index: 749

Text #4

Max Range: 3.3768. Min Range: -3.3768

Max Act: 2.8084. Min Act: -0.0000

Data Index: 1036279 (The Pile)

Max Activating Token Index: 521

Text #5

Max Range: 3.3768. Min Range: -3.3768

Max Act: 2.9307. Min Act: -0.0000

Data Index: 1382806 (The Pile)

Max Activating Token Index: 181

Text #6

Max Range: 3.3768. Min Range: -3.3768

Max Act: 2.4435. Min Act: -0.0000

Data Index: 1181596 (The Pile)

Max Activating Token Index: 169

Text #7

Max Range: 3.3768. Min Range: -3.3768

Max Act: 2.4060. Min Act: -0.0000

Data Index: 1438890 (The Pile)

Max Activating Token Index: 220

Text #8

Max Range: 3.3768. Min Range: -3.3768

Max Act: 2.9572. Min Act: -0.0000

Data Index: 277309 (The Pile)

Max Activating Token Index: 994

Text #9

Max Range: 3.3768. Min Range: -3.3768

Max Act: 2.4989. Min Act: -0.0000

Data Index: 1376421 (The Pile)

Max Activating Token Index: 532

Text #10

Max Range: 3.3768. Min Range: -3.3768

Max Act: 2.3877. Min Act: -0.0000

Data Index: 1431731 (The Pile)

Max Activating Token Index: 300

Text #11

Max Range: 3.3768. Min Range: -3.3768

Max Act: 2.1922. Min Act: -0.0000

Data Index: 1569987 (The Pile)

Max Activating Token Index: 63

Text #12

Max Range: 3.3768. Min Range: -3.3768

Max Act: 2.2550. Min Act: -0.0000

Data Index: 466469 (The Pile)

Max Activating Token Index: 211

Text #13

Max Range: 3.3768. Min Range: -3.3768

Max Act: 2.2508. Min Act: -0.0000

Data Index: 1943261 (The Pile)

Max Activating Token Index: 197

Text #14

Max Range: 3.3768. Min Range: -3.3768

Max Act: 2.4821. Min Act: -0.0000

Data Index: 668445 (The Pile)

Max Activating Token Index: 117

Text #15

Max Range: 3.3768. Min Range: -3.3768

Max Act: 2.1000. Min Act: -0.0000

Data Index: 1119462 (The Pile)

Max Activating Token Index: 900

Text #16

Max Range: 3.3768. Min Range: -3.3768

Max Act: 2.1910. Min Act: -0.0000

Data Index: 1288620 (The Pile)

Max Activating Token Index: 607

Text #17

Max Range: 3.3768. Min Range: -3.3768

Max Act: 2.2718. Min Act: -0.0000

Data Index: 1247745 (The Pile)

Max Activating Token Index: 790

Text #18

Max Range: 3.3768. Min Range: -3.3768

Max Act: 2.0735. Min Act: -0.0000

Data Index: 1454189 (The Pile)

Max Activating Token Index: 528

Text #19

Max Range: 3.3768. Min Range: -3.3768

Max Act: 2.1563. Min Act: -0.0000

Data Index: 1077080 (The Pile)

Max Activating Token Index: 673