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

Dataset: The Pile

Neuron 3427 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5674. Min Range: -1.5674

Max Act: 1.4956. Min Act: -0.0000

Data Index: 449823 (The Pile)

Max Activating Token Index: 157

Text #1

Max Range: 1.5674. Min Range: -1.5674

Max Act: 1.3700. Min Act: -0.0000

Data Index: 1162919 (The Pile)

Max Activating Token Index: 102

Text #2

Max Range: 1.5674. Min Range: -1.5674

Max Act: 1.3756. Min Act: -0.0000

Data Index: 1822898 (The Pile)

Max Activating Token Index: 791

Text #3

Max Range: 1.5674. Min Range: -1.5674

Max Act: 1.3336. Min Act: -0.0000

Data Index: 1387679 (The Pile)

Max Activating Token Index: 385

Text #4

Max Range: 1.5674. Min Range: -1.5674

Max Act: 1.2541. Min Act: -0.0000

Data Index: 1136563 (The Pile)

Max Activating Token Index: 210

Text #5

Max Range: 1.5674. Min Range: -1.5674

Max Act: 1.3358. Min Act: -0.0000

Data Index: 142602 (The Pile)

Max Activating Token Index: 540

Text #6

Max Range: 1.5674. Min Range: -1.5674

Max Act: 1.2469. Min Act: -0.0000

Data Index: 349385 (The Pile)

Max Activating Token Index: 211

Text #7

Max Range: 1.5674. Min Range: -1.5674

Max Act: 1.5674. Min Act: -0.0000

Data Index: 1467578 (The Pile)

Max Activating Token Index: 753

Text #8

Max Range: 1.5674. Min Range: -1.5674

Max Act: 1.2045. Min Act: -0.0000

Data Index: 1763576 (The Pile)

Max Activating Token Index: 293

Text #9

Max Range: 1.5674. Min Range: -1.5674

Max Act: 1.3460. Min Act: -0.0000

Data Index: 1826473 (The Pile)

Max Activating Token Index: 610

Text #10

Max Range: 1.5674. Min Range: -1.5674

Max Act: 1.2613. Min Act: -0.0000

Data Index: 1461687 (The Pile)

Max Activating Token Index: 379

Text #11

Max Range: 1.5674. Min Range: -1.5674

Max Act: 1.1481. Min Act: -0.0000

Data Index: 1207549 (The Pile)

Max Activating Token Index: 707

Text #12

Max Range: 1.5674. Min Range: -1.5674

Max Act: 1.3150. Min Act: -0.0000

Data Index: 1186952 (The Pile)

Max Activating Token Index: 203

Text #13

Max Range: 1.5674. Min Range: -1.5674

Max Act: 1.2033. Min Act: -0.0000

Data Index: 1461237 (The Pile)

Max Activating Token Index: 460

Text #14

Max Range: 1.5674. Min Range: -1.5674

Max Act: 1.1746. Min Act: -0.0000

Data Index: 1111752 (The Pile)

Max Activating Token Index: 130

Text #15

Max Range: 1.5674. Min Range: -1.5674

Max Act: 1.2434. Min Act: -0.0000

Data Index: 1142266 (The Pile)

Max Activating Token Index: 296

Text #16

Max Range: 1.5674. Min Range: -1.5674

Max Act: 1.2023. Min Act: -0.0000

Data Index: 586809 (The Pile)

Max Activating Token Index: 416

Text #17

Max Range: 1.5674. Min Range: -1.5674

Max Act: 1.1551. Min Act: -0.0000

Data Index: 797065 (The Pile)

Max Activating Token Index: 333

Text #18

Max Range: 1.5674. Min Range: -1.5674

Max Act: 1.0728. Min Act: -0.0000

Data Index: 1436186 (The Pile)

Max Activating Token Index: 503

Text #19

Max Range: 1.5674. Min Range: -1.5674

Max Act: 1.0918. Min Act: -0.0000

Data Index: 682264 (The Pile)

Max Activating Token Index: 351