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

Dataset: The Pile

Neuron 4122 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: 2.0077. Min Range: -2.0077

Max Act: 2.0077. Min Act: -0.0000

Data Index: 1433497 (The Pile)

Max Activating Token Index: 904

Text #1

Max Range: 2.0077. Min Range: -2.0077

Max Act: 1.7844. Min Act: -0.0000

Data Index: 660036 (The Pile)

Max Activating Token Index: 500

Text #2

Max Range: 2.0077. Min Range: -2.0077

Max Act: 1.7639. Min Act: -0.0000

Data Index: 1359143 (The Pile)

Max Activating Token Index: 648

Text #3

Max Range: 2.0077. Min Range: -2.0077

Max Act: 1.8012. Min Act: -0.0000

Data Index: 946924 (The Pile)

Max Activating Token Index: 72

Text #4

Max Range: 2.0077. Min Range: -2.0077

Max Act: 1.6933. Min Act: -0.0000

Data Index: 1061756 (The Pile)

Max Activating Token Index: 184

Text #5

Max Range: 2.0077. Min Range: -2.0077

Max Act: 1.6668. Min Act: -0.0000

Data Index: 1730424 (The Pile)

Max Activating Token Index: 384

Text #6

Max Range: 2.0077. Min Range: -2.0077

Max Act: 1.6814. Min Act: -0.0000

Data Index: 1952984 (The Pile)

Max Activating Token Index: 517

Text #7

Max Range: 2.0077. Min Range: -2.0077

Max Act: 1.6141. Min Act: -0.0000

Data Index: 1540609 (The Pile)

Max Activating Token Index: 474

Text #8

Max Range: 2.0077. Min Range: -2.0077

Max Act: 1.5536. Min Act: -0.0000

Data Index: 1009512 (The Pile)

Max Activating Token Index: 495

Text #9

Max Range: 2.0077. Min Range: -2.0077

Max Act: 1.5067. Min Act: -0.0000

Data Index: 988886 (The Pile)

Max Activating Token Index: 497

Text #10

Max Range: 2.0077. Min Range: -2.0077

Max Act: 1.4168. Min Act: 0.0000

Data Index: 995023 (The Pile)

Max Activating Token Index: 760

Text #11

Max Range: 2.0077. Min Range: -2.0077

Max Act: 1.4740. Min Act: -0.0000

Data Index: 1477203 (The Pile)

Max Activating Token Index: 331

Text #12

Max Range: 2.0077. Min Range: -2.0077

Max Act: 1.4578. Min Act: -0.0000

Data Index: 1893765 (The Pile)

Max Activating Token Index: 327

Text #13

Max Range: 2.0077. Min Range: -2.0077

Max Act: 1.4606. Min Act: -0.0000

Data Index: 151455 (The Pile)

Max Activating Token Index: 171

Text #14

Max Range: 2.0077. Min Range: -2.0077

Max Act: 1.4595. Min Act: -0.0000

Data Index: 1018807 (The Pile)

Max Activating Token Index: 564

Text #15

Max Range: 2.0077. Min Range: -2.0077

Max Act: 1.3628. Min Act: 0.0000

Data Index: 819416 (The Pile)

Max Activating Token Index: 1014

Text #16

Max Range: 2.0077. Min Range: -2.0077

Max Act: 1.4481. Min Act: -0.0000

Data Index: 306856 (The Pile)

Max Activating Token Index: 932

Text #17

Max Range: 2.0077. Min Range: -2.0077

Max Act: 1.4514. Min Act: -0.0000

Data Index: 1837130 (The Pile)

Max Activating Token Index: 560

Text #18

Max Range: 2.0077. Min Range: -2.0077

Max Act: 1.4234. Min Act: -0.0000

Data Index: 761802 (The Pile)

Max Activating Token Index: 1016

Text #19

Max Range: 2.0077. Min Range: -2.0077

Max Act: 1.4230. Min Act: -0.0000

Data Index: 506185 (The Pile)

Max Activating Token Index: 530