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

Dataset: The Pile

Neuron 3577 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3276. Min Range: -1.3276

Max Act: 1.3276. Min Act: -0.0000

Data Index: 1983367 (The Pile)

Max Activating Token Index: 97

Text #1

Max Range: 1.3276. Min Range: -1.3276

Max Act: 1.0197. Min Act: -0.0000

Data Index: 524018 (The Pile)

Max Activating Token Index: 679

Text #2

Max Range: 1.3276. Min Range: -1.3276

Max Act: 0.9794. Min Act: -0.0000

Data Index: 1401594 (The Pile)

Max Activating Token Index: 951

Text #3

Max Range: 1.3276. Min Range: -1.3276

Max Act: 1.0291. Min Act: 0.0000

Data Index: 988508 (The Pile)

Max Activating Token Index: 539

Text #4

Max Range: 1.3276. Min Range: -1.3276

Max Act: 1.0374. Min Act: -0.0000

Data Index: 502834 (The Pile)

Max Activating Token Index: 993

Text #5

Max Range: 1.3276. Min Range: -1.3276

Max Act: 0.9855. Min Act: 0.0000

Data Index: 97203 (The Pile)

Max Activating Token Index: 717

Text #6

Max Range: 1.3276. Min Range: -1.3276

Max Act: 0.9023. Min Act: 0.0000

Data Index: 1737137 (The Pile)

Max Activating Token Index: 905

Text #7

Max Range: 1.3276. Min Range: -1.3276

Max Act: 0.9838. Min Act: 0.0000

Data Index: 117425 (The Pile)

Max Activating Token Index: 455

Text #8

Max Range: 1.3276. Min Range: -1.3276

Max Act: 0.9826. Min Act: -0.0000

Data Index: 1533886 (The Pile)

Max Activating Token Index: 46

Text #9

Max Range: 1.3276. Min Range: -1.3276

Max Act: 0.9176. Min Act: -0.0000

Data Index: 1510967 (The Pile)

Max Activating Token Index: 349

Text #10

Max Range: 1.3276. Min Range: -1.3276

Max Act: 0.7576. Min Act: -0.0000

Data Index: 1797484 (The Pile)

Max Activating Token Index: 794

Text #11

Max Range: 1.3276. Min Range: -1.3276

Max Act: 0.9071. Min Act: -0.0000

Data Index: 273827 (The Pile)

Max Activating Token Index: 300

Text #12

Max Range: 1.3276. Min Range: -1.3276

Max Act: 0.8634. Min Act: -0.0000

Data Index: 889215 (The Pile)

Max Activating Token Index: 560

Text #13

Max Range: 1.3276. Min Range: -1.3276

Max Act: 0.8165. Min Act: -0.0000

Data Index: 1330356 (The Pile)

Max Activating Token Index: 249

Text #14

Max Range: 1.3276. Min Range: -1.3276

Max Act: 0.8115. Min Act: -0.0000

Data Index: 1590266 (The Pile)

Max Activating Token Index: 802

Text #15

Max Range: 1.3276. Min Range: -1.3276

Max Act: 0.7969. Min Act: 0.0000

Data Index: 795923 (The Pile)

Max Activating Token Index: 687

Text #16

Max Range: 1.3276. Min Range: -1.3276

Max Act: 0.7686. Min Act: 0.0001

Data Index: 188153 (The Pile)

Max Activating Token Index: 988

Text #17

Max Range: 1.3276. Min Range: -1.3276

Max Act: 0.8187. Min Act: -0.0000

Data Index: 513383 (The Pile)

Max Activating Token Index: 162

Text #18

Max Range: 1.3276. Min Range: -1.3276

Max Act: 0.8100. Min Act: -0.0000

Data Index: 496340 (The Pile)

Max Activating Token Index: 157

Text #19

Max Range: 1.3276. Min Range: -1.3276

Max Act: 0.7940. Min Act: -0.0000

Data Index: 1341401 (The Pile)

Max Activating Token Index: 990