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

Dataset: The Pile

Neuron 227 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8721. Min Range: -1.8721

Max Act: 1.8498. Min Act: -0.0000

Data Index: 1235069 (The Pile)

Max Activating Token Index: 343

Text #1

Max Range: 1.8721. Min Range: -1.8721

Max Act: 1.8720. Min Act: -0.0000

Data Index: 137874 (The Pile)

Max Activating Token Index: 310

Text #2

Max Range: 1.8721. Min Range: -1.8721

Max Act: 1.8721. Min Act: -0.0000

Data Index: 1988464 (The Pile)

Max Activating Token Index: 583

Text #3

Max Range: 1.8721. Min Range: -1.8721

Max Act: 1.6292. Min Act: -0.0000

Data Index: 719964 (The Pile)

Max Activating Token Index: 178

Text #4

Max Range: 1.8721. Min Range: -1.8721

Max Act: 1.6139. Min Act: -0.0000

Data Index: 756426 (The Pile)

Max Activating Token Index: 96

Text #5

Max Range: 1.8721. Min Range: -1.8721

Max Act: 1.6442. Min Act: -0.0000

Data Index: 1123683 (The Pile)

Max Activating Token Index: 373

Text #6

Max Range: 1.8721. Min Range: -1.8721

Max Act: 1.7288. Min Act: -0.0000

Data Index: 317571 (The Pile)

Max Activating Token Index: 408

Text #7

Max Range: 1.8721. Min Range: -1.8721

Max Act: 1.6704. Min Act: -0.0000

Data Index: 1262018 (The Pile)

Max Activating Token Index: 91

Text #8

Max Range: 1.8721. Min Range: -1.8721

Max Act: 1.6110. Min Act: -0.0000

Data Index: 1938540 (The Pile)

Max Activating Token Index: 222

Text #9

Max Range: 1.8721. Min Range: -1.8721

Max Act: 1.6130. Min Act: -0.0000

Data Index: 362118 (The Pile)

Max Activating Token Index: 304

Text #10

Max Range: 1.8721. Min Range: -1.8721

Max Act: 1.5179. Min Act: -0.0000

Data Index: 33341 (The Pile)

Max Activating Token Index: 106

Text #11

Max Range: 1.8721. Min Range: -1.8721

Max Act: 1.4898. Min Act: -0.0000

Data Index: 58711 (The Pile)

Max Activating Token Index: 637

Text #12

Max Range: 1.8721. Min Range: -1.8721

Max Act: 1.5291. Min Act: -0.0000

Data Index: 1773810 (The Pile)

Max Activating Token Index: 333

Text #13

Max Range: 1.8721. Min Range: -1.8721

Max Act: 1.5627. Min Act: -0.0000

Data Index: 113162 (The Pile)

Max Activating Token Index: 368

Text #14

Max Range: 1.8721. Min Range: -1.8721

Max Act: 1.5341. Min Act: -0.0000

Data Index: 316618 (The Pile)

Max Activating Token Index: 296

Text #15

Max Range: 1.8721. Min Range: -1.8721

Max Act: 1.5253. Min Act: -0.0000

Data Index: 665280 (The Pile)

Max Activating Token Index: 178

Text #16

Max Range: 1.8721. Min Range: -1.8721

Max Act: 1.4778. Min Act: -0.0000

Data Index: 614314 (The Pile)

Max Activating Token Index: 333

Text #17

Max Range: 1.8721. Min Range: -1.8721

Max Act: 1.4504. Min Act: -0.0000

Data Index: 1611946 (The Pile)

Max Activating Token Index: 580

Text #18

Max Range: 1.8721. Min Range: -1.8721

Max Act: 1.5757. Min Act: -0.0000

Data Index: 669938 (The Pile)

Max Activating Token Index: 617

Text #19

Max Range: 1.8721. Min Range: -1.8721

Max Act: 1.4926. Min Act: -0.0000

Data Index: 1886745 (The Pile)

Max Activating Token Index: 443