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

Dataset: The Pile

Neuron 755 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9758. Min Range: -1.9758

Max Act: 1.9758. Min Act: -0.0000

Data Index: 1764734 (The Pile)

Max Activating Token Index: 744

Text #1

Max Range: 1.9758. Min Range: -1.9758

Max Act: 1.9562. Min Act: -0.0000

Data Index: 489214 (The Pile)

Max Activating Token Index: 379

Text #2

Max Range: 1.9758. Min Range: -1.9758

Max Act: 1.7861. Min Act: -0.0000

Data Index: 977365 (The Pile)

Max Activating Token Index: 552

Text #3

Max Range: 1.9758. Min Range: -1.9758

Max Act: 1.8916. Min Act: -0.0000

Data Index: 1314479 (The Pile)

Max Activating Token Index: 766

Text #4

Max Range: 1.9758. Min Range: -1.9758

Max Act: 1.8140. Min Act: -0.0000

Data Index: 1568148 (The Pile)

Max Activating Token Index: 274

Text #5

Max Range: 1.9758. Min Range: -1.9758

Max Act: 1.8843. Min Act: -0.0000

Data Index: 462558 (The Pile)

Max Activating Token Index: 407

Text #6

Max Range: 1.9758. Min Range: -1.9758

Max Act: 1.6846. Min Act: -0.0000

Data Index: 1048708 (The Pile)

Max Activating Token Index: 536

Text #7

Max Range: 1.9758. Min Range: -1.9758

Max Act: 1.6354. Min Act: -0.0000

Data Index: 1205268 (The Pile)

Max Activating Token Index: 669

Text #8

Max Range: 1.9758. Min Range: -1.9758

Max Act: 1.8246. Min Act: -0.0000

Data Index: 414833 (The Pile)

Max Activating Token Index: 487

Text #9

Max Range: 1.9758. Min Range: -1.9758

Max Act: 1.8114. Min Act: -0.0000

Data Index: 86936 (The Pile)

Max Activating Token Index: 275

Text #10

Max Range: 1.9758. Min Range: -1.9758

Max Act: 1.6648. Min Act: -0.0000

Data Index: 38819 (The Pile)

Max Activating Token Index: 728

Text #11

Max Range: 1.9758. Min Range: -1.9758

Max Act: 1.6016. Min Act: -0.0000

Data Index: 1049841 (The Pile)

Max Activating Token Index: 353

Text #12

Max Range: 1.9758. Min Range: -1.9758

Max Act: 1.5115. Min Act: -0.0000

Data Index: 457029 (The Pile)

Max Activating Token Index: 962

Text #13

Max Range: 1.9758. Min Range: -1.9758

Max Act: 1.4843. Min Act: -0.0000

Data Index: 1359389 (The Pile)

Max Activating Token Index: 347

Text #14

Max Range: 1.9758. Min Range: -1.9758

Max Act: 1.5849. Min Act: -0.0000

Data Index: 58865 (The Pile)

Max Activating Token Index: 781

Text #15

Max Range: 1.9758. Min Range: -1.9758

Max Act: 1.5190. Min Act: -0.0000

Data Index: 381462 (The Pile)

Max Activating Token Index: 518

Text #16

Max Range: 1.9758. Min Range: -1.9758

Max Act: 1.4284. Min Act: -0.0000

Data Index: 1976613 (The Pile)

Max Activating Token Index: 972

Text #17

Max Range: 1.9758. Min Range: -1.9758

Max Act: 1.5943. Min Act: -0.0000

Data Index: 318034 (The Pile)

Max Activating Token Index: 480

Text #18

Max Range: 1.9758. Min Range: -1.9758

Max Act: 1.5117. Min Act: -0.0000

Data Index: 945272 (The Pile)

Max Activating Token Index: 365

Text #19

Max Range: 1.9758. Min Range: -1.9758

Max Act: 1.4134. Min Act: -0.0000

Data Index: 761532 (The Pile)

Max Activating Token Index: 538