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

Dataset: The Pile

Neuron 1130 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: 0.8486. Min Range: -0.8486

Max Act: 0.8486. Min Act: -0.0000

Data Index: 777120 (The Pile)

Max Activating Token Index: 815

Text #1

Max Range: 0.8486. Min Range: -0.8486

Max Act: 0.5769. Min Act: -0.0000

Data Index: 789915 (The Pile)

Max Activating Token Index: 579

Text #2

Max Range: 0.8486. Min Range: -0.8486

Max Act: 0.5476. Min Act: -0.0000

Data Index: 1821017 (The Pile)

Max Activating Token Index: 953

Text #3

Max Range: 0.8486. Min Range: -0.8486

Max Act: 0.5506. Min Act: -0.0000

Data Index: 296167 (The Pile)

Max Activating Token Index: 512

Text #4

Max Range: 0.8486. Min Range: -0.8486

Max Act: 0.5314. Min Act: -0.0000

Data Index: 1514359 (The Pile)

Max Activating Token Index: 259

Text #5

Max Range: 0.8486. Min Range: -0.8486

Max Act: 0.5413. Min Act: -0.0000

Data Index: 765128 (The Pile)

Max Activating Token Index: 46

Text #6

Max Range: 0.8486. Min Range: -0.8486

Max Act: 0.5752. Min Act: -0.0000

Data Index: 481266 (The Pile)

Max Activating Token Index: 665

Text #7

Max Range: 0.8486. Min Range: -0.8486

Max Act: 0.5522. Min Act: -0.0000

Data Index: 517876 (The Pile)

Max Activating Token Index: 432

Text #8

Max Range: 0.8486. Min Range: -0.8486

Max Act: 0.5133. Min Act: -0.0000

Data Index: 861206 (The Pile)

Max Activating Token Index: 454

Text #9

Max Range: 0.8486. Min Range: -0.8486

Max Act: 0.4985. Min Act: -0.0000

Data Index: 318180 (The Pile)

Max Activating Token Index: 117

Text #10

Max Range: 0.8486. Min Range: -0.8486

Max Act: 0.4741. Min Act: -0.0000

Data Index: 179966 (The Pile)

Max Activating Token Index: 819

Text #11

Max Range: 0.8486. Min Range: -0.8486

Max Act: 0.4573. Min Act: -0.0000

Data Index: 1567945 (The Pile)

Max Activating Token Index: 36

Text #12

Max Range: 0.8486. Min Range: -0.8486

Max Act: 0.5029. Min Act: -0.0000

Data Index: 1944870 (The Pile)

Max Activating Token Index: 132

Text #13

Max Range: 0.8486. Min Range: -0.8486

Max Act: 0.4670. Min Act: -0.0000

Data Index: 912188 (The Pile)

Max Activating Token Index: 185

Text #14

Max Range: 0.8486. Min Range: -0.8486

Max Act: 0.5345. Min Act: -0.0000

Data Index: 713536 (The Pile)

Max Activating Token Index: 639

Text #15

Max Range: 0.8486. Min Range: -0.8486

Max Act: 0.4855. Min Act: -0.0000

Data Index: 836448 (The Pile)

Max Activating Token Index: 485

Text #16

Max Range: 0.8486. Min Range: -0.8486

Max Act: 0.4842. Min Act: -0.0000

Data Index: 1732675 (The Pile)

Max Activating Token Index: 225

Text #17

Max Range: 0.8486. Min Range: -0.8486

Max Act: 0.4919. Min Act: -0.0000

Data Index: 1540295 (The Pile)

Max Activating Token Index: 5

Text #18

Max Range: 0.8486. Min Range: -0.8486

Max Act: 0.4673. Min Act: -0.0000

Data Index: 762161 (The Pile)

Max Activating Token Index: 206

Text #19

Max Range: 0.8486. Min Range: -0.8486

Max Act: 0.4799. Min Act: -0.0000

Data Index: 1438849 (The Pile)

Max Activating Token Index: 326