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

Dataset: The Pile

Neuron 2755 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: 1.3286. Min Range: -1.3286

Max Act: 1.3286. Min Act: -0.0000

Data Index: 93318 (The Pile)

Max Activating Token Index: 278

Text #1

Max Range: 1.3286. Min Range: -1.3286

Max Act: 1.2373. Min Act: -0.0000

Data Index: 360246 (The Pile)

Max Activating Token Index: 780

Text #2

Max Range: 1.3286. Min Range: -1.3286

Max Act: 1.1843. Min Act: -0.0000

Data Index: 1241533 (The Pile)

Max Activating Token Index: 161

Text #3

Max Range: 1.3286. Min Range: -1.3286

Max Act: 1.2526. Min Act: -0.0000

Data Index: 1810303 (The Pile)

Max Activating Token Index: 960

Text #4

Max Range: 1.3286. Min Range: -1.3286

Max Act: 1.0060. Min Act: -0.0000

Data Index: 1586565 (The Pile)

Max Activating Token Index: 29

Text #5

Max Range: 1.3286. Min Range: -1.3286

Max Act: 1.0086. Min Act: -0.0000

Data Index: 697853 (The Pile)

Max Activating Token Index: 695

Text #6

Max Range: 1.3286. Min Range: -1.3286

Max Act: 0.9746. Min Act: -0.0000

Data Index: 862989 (The Pile)

Max Activating Token Index: 434

Text #7

Max Range: 1.3286. Min Range: -1.3286

Max Act: 0.9507. Min Act: -0.0000

Data Index: 613090 (The Pile)

Max Activating Token Index: 469

Text #8

Max Range: 1.3286. Min Range: -1.3286

Max Act: 0.9406. Min Act: -0.0000

Data Index: 693710 (The Pile)

Max Activating Token Index: 787

Text #9

Max Range: 1.3286. Min Range: -1.3286

Max Act: 0.9113. Min Act: -0.0000

Data Index: 1489739 (The Pile)

Max Activating Token Index: 468

Text #10

Max Range: 1.3286. Min Range: -1.3286

Max Act: 0.9119. Min Act: -0.0000

Data Index: 923242 (The Pile)

Max Activating Token Index: 443

Text #11

Max Range: 1.3286. Min Range: -1.3286

Max Act: 0.9229. Min Act: -0.0000

Data Index: 1626921 (The Pile)

Max Activating Token Index: 447

Text #12

Max Range: 1.3286. Min Range: -1.3286

Max Act: 0.9236. Min Act: -0.0000

Data Index: 1055921 (The Pile)

Max Activating Token Index: 936

Text #13

Max Range: 1.3286. Min Range: -1.3286

Max Act: 0.9097. Min Act: -0.0000

Data Index: 148031 (The Pile)

Max Activating Token Index: 522

Text #14

Max Range: 1.3286. Min Range: -1.3286

Max Act: 0.8819. Min Act: -0.0000

Data Index: 963503 (The Pile)

Max Activating Token Index: 569

Text #15

Max Range: 1.3286. Min Range: -1.3286

Max Act: 0.9082. Min Act: -0.0000

Data Index: 319157 (The Pile)

Max Activating Token Index: 905

Text #16

Max Range: 1.3286. Min Range: -1.3286

Max Act: 0.8807. Min Act: -0.0000

Data Index: 1337515 (The Pile)

Max Activating Token Index: 764

Text #17

Max Range: 1.3286. Min Range: -1.3286

Max Act: 0.8469. Min Act: -0.0000

Data Index: 1606754 (The Pile)

Max Activating Token Index: 305

Text #18

Max Range: 1.3286. Min Range: -1.3286

Max Act: 0.8620. Min Act: -0.0000

Data Index: 369861 (The Pile)

Max Activating Token Index: 275

Text #19

Max Range: 1.3286. Min Range: -1.3286

Max Act: 0.8578. Min Act: -0.0000

Data Index: 1355642 (The Pile)

Max Activating Token Index: 338