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

Dataset: The Pile

Neuron 4677 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: 1.5468. Min Range: -1.5468

Max Act: 1.5468. Min Act: -0.0000

Data Index: 1920118 (The Pile)

Max Activating Token Index: 456

Text #1

Max Range: 1.5468. Min Range: -1.5468

Max Act: 1.4919. Min Act: -0.0000

Data Index: 693319 (The Pile)

Max Activating Token Index: 287

Text #2

Max Range: 1.5468. Min Range: -1.5468

Max Act: 1.2785. Min Act: -0.0000

Data Index: 1607237 (The Pile)

Max Activating Token Index: 103

Text #3

Max Range: 1.5468. Min Range: -1.5468

Max Act: 1.2348. Min Act: -0.0000

Data Index: 628454 (The Pile)

Max Activating Token Index: 614

Text #4

Max Range: 1.5468. Min Range: -1.5468

Max Act: 1.2628. Min Act: -0.0000

Data Index: 1264787 (The Pile)

Max Activating Token Index: 52

Text #5

Max Range: 1.5468. Min Range: -1.5468

Max Act: 1.1208. Min Act: -0.0000

Data Index: 323519 (The Pile)

Max Activating Token Index: 693

Text #6

Max Range: 1.5468. Min Range: -1.5468

Max Act: 1.1973. Min Act: -0.0000

Data Index: 1662545 (The Pile)

Max Activating Token Index: 393

Text #7

Max Range: 1.5468. Min Range: -1.5468

Max Act: 1.1143. Min Act: -0.0000

Data Index: 1695569 (The Pile)

Max Activating Token Index: 480

Text #8

Max Range: 1.5468. Min Range: -1.5468

Max Act: 1.1394. Min Act: -0.0000

Data Index: 439281 (The Pile)

Max Activating Token Index: 69

Text #9

Max Range: 1.5468. Min Range: -1.5468

Max Act: 1.1041. Min Act: -0.0000

Data Index: 1570528 (The Pile)

Max Activating Token Index: 532

Text #10

Max Range: 1.5468. Min Range: -1.5468

Max Act: 1.0708. Min Act: -0.0000

Data Index: 1585642 (The Pile)

Max Activating Token Index: 224

Text #11

Max Range: 1.5468. Min Range: -1.5468

Max Act: 1.0987. Min Act: -0.0000

Data Index: 1370846 (The Pile)

Max Activating Token Index: 277

Text #12

Max Range: 1.5468. Min Range: -1.5468

Max Act: 1.0052. Min Act: -0.0000

Data Index: 1049276 (The Pile)

Max Activating Token Index: 143

Text #13

Max Range: 1.5468. Min Range: -1.5468

Max Act: 1.0230. Min Act: -0.0000

Data Index: 1305865 (The Pile)

Max Activating Token Index: 395

Text #14

Max Range: 1.5468. Min Range: -1.5468

Max Act: 1.0409. Min Act: -0.0000

Data Index: 1539939 (The Pile)

Max Activating Token Index: 123

Text #15

Max Range: 1.5468. Min Range: -1.5468

Max Act: 0.9739. Min Act: -0.0000

Data Index: 252762 (The Pile)

Max Activating Token Index: 655

Text #16

Max Range: 1.5468. Min Range: -1.5468

Max Act: 0.9746. Min Act: -0.0000

Data Index: 1074568 (The Pile)

Max Activating Token Index: 209

Text #17

Max Range: 1.5468. Min Range: -1.5468

Max Act: 0.9941. Min Act: -0.0000

Data Index: 1208371 (The Pile)

Max Activating Token Index: 43

Text #18

Max Range: 1.5468. Min Range: -1.5468

Max Act: 1.0604. Min Act: -0.0000

Data Index: 1408909 (The Pile)

Max Activating Token Index: 677

Text #19

Max Range: 1.5468. Min Range: -1.5468

Max Act: 0.9957. Min Act: -0.0000

Data Index: 1973517 (The Pile)

Max Activating Token Index: 409