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

Dataset: The Pile

Neuron 2756 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4592. Min Range: -1.4592

Max Act: 1.4592. Min Act: -0.0000

Data Index: 1131941 (The Pile)

Max Activating Token Index: 286

Text #1

Max Range: 1.4592. Min Range: -1.4592

Max Act: 1.4471. Min Act: -0.0000

Data Index: 1137117 (The Pile)

Max Activating Token Index: 277

Text #2

Max Range: 1.4592. Min Range: -1.4592

Max Act: 1.1703. Min Act: -0.0000

Data Index: 419768 (The Pile)

Max Activating Token Index: 405

Text #3

Max Range: 1.4592. Min Range: -1.4592

Max Act: 1.1719. Min Act: -0.0000

Data Index: 1781116 (The Pile)

Max Activating Token Index: 337

Text #4

Max Range: 1.4592. Min Range: -1.4592

Max Act: 1.0320. Min Act: -0.0000

Data Index: 1996044 (The Pile)

Max Activating Token Index: 479

Text #5

Max Range: 1.4592. Min Range: -1.4592

Max Act: 1.0910. Min Act: -0.0000

Data Index: 770897 (The Pile)

Max Activating Token Index: 443

Text #6

Max Range: 1.4592. Min Range: -1.4592

Max Act: 0.9834. Min Act: -0.0000

Data Index: 941817 (The Pile)

Max Activating Token Index: 393

Text #7

Max Range: 1.4592. Min Range: -1.4592

Max Act: 1.0043. Min Act: -0.0000

Data Index: 1880363 (The Pile)

Max Activating Token Index: 662

Text #8

Max Range: 1.4592. Min Range: -1.4592

Max Act: 1.1270. Min Act: -0.0000

Data Index: 977019 (The Pile)

Max Activating Token Index: 331

Text #9

Max Range: 1.4592. Min Range: -1.4592

Max Act: 0.9318. Min Act: -0.0000

Data Index: 864898 (The Pile)

Max Activating Token Index: 580

Text #10

Max Range: 1.4592. Min Range: -1.4592

Max Act: 0.9284. Min Act: -0.0000

Data Index: 1223090 (The Pile)

Max Activating Token Index: 865

Text #11

Max Range: 1.4592. Min Range: -1.4592

Max Act: 0.9893. Min Act: -0.0000

Data Index: 395181 (The Pile)

Max Activating Token Index: 433

Text #12

Max Range: 1.4592. Min Range: -1.4592

Max Act: 1.0289. Min Act: -0.0000

Data Index: 1884539 (The Pile)

Max Activating Token Index: 511

Text #13

Max Range: 1.4592. Min Range: -1.4592

Max Act: 0.8831. Min Act: -0.0000

Data Index: 1831359 (The Pile)

Max Activating Token Index: 537

Text #14

Max Range: 1.4592. Min Range: -1.4592

Max Act: 1.0094. Min Act: -0.0000

Data Index: 184733 (The Pile)

Max Activating Token Index: 479

Text #15

Max Range: 1.4592. Min Range: -1.4592

Max Act: 0.8341. Min Act: -0.0000

Data Index: 60226 (The Pile)

Max Activating Token Index: 657

Text #16

Max Range: 1.4592. Min Range: -1.4592

Max Act: 0.7971. Min Act: -0.0000

Data Index: 1549999 (The Pile)

Max Activating Token Index: 640

Text #17

Max Range: 1.4592. Min Range: -1.4592

Max Act: 0.8144. Min Act: -0.0000

Data Index: 726361 (The Pile)

Max Activating Token Index: 414

Text #18

Max Range: 1.4592. Min Range: -1.4592

Max Act: 0.8580. Min Act: -0.0000

Data Index: 290148 (The Pile)

Max Activating Token Index: 847

Text #19

Max Range: 1.4592. Min Range: -1.4592

Max Act: 0.6271. Min Act: -0.0000

Data Index: 1940726 (The Pile)

Max Activating Token Index: 800