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

Dataset: The Pile

Neuron 3997 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2363. Min Range: -1.2363

Max Act: 1.2294. Min Act: -0.0000

Data Index: 1289178 (The Pile)

Max Activating Token Index: 56

Text #1

Max Range: 1.2363. Min Range: -1.2363

Max Act: 1.2363. Min Act: -0.0000

Data Index: 847289 (The Pile)

Max Activating Token Index: 121

Text #2

Max Range: 1.2363. Min Range: -1.2363

Max Act: 1.0691. Min Act: -0.0000

Data Index: 757003 (The Pile)

Max Activating Token Index: 245

Text #3

Max Range: 1.2363. Min Range: -1.2363

Max Act: 1.1131. Min Act: -0.0000

Data Index: 1731654 (The Pile)

Max Activating Token Index: 694

Text #4

Max Range: 1.2363. Min Range: -1.2363

Max Act: 1.1120. Min Act: -0.0000

Data Index: 331471 (The Pile)

Max Activating Token Index: 308

Text #5

Max Range: 1.2363. Min Range: -1.2363

Max Act: 0.9828. Min Act: -0.0000

Data Index: 1846045 (The Pile)

Max Activating Token Index: 537

Text #6

Max Range: 1.2363. Min Range: -1.2363

Max Act: 1.0331. Min Act: -0.0000

Data Index: 220944 (The Pile)

Max Activating Token Index: 392

Text #7

Max Range: 1.2363. Min Range: -1.2363

Max Act: 0.8676. Min Act: -0.0000

Data Index: 1701490 (The Pile)

Max Activating Token Index: 602

Text #8

Max Range: 1.2363. Min Range: -1.2363

Max Act: 0.9066. Min Act: -0.0000

Data Index: 542161 (The Pile)

Max Activating Token Index: 422

Text #9

Max Range: 1.2363. Min Range: -1.2363

Max Act: 0.9065. Min Act: -0.0000

Data Index: 952712 (The Pile)

Max Activating Token Index: 727

Text #10

Max Range: 1.2363. Min Range: -1.2363

Max Act: 0.9116. Min Act: -0.0000

Data Index: 1510251 (The Pile)

Max Activating Token Index: 611

Text #11

Max Range: 1.2363. Min Range: -1.2363

Max Act: 0.8617. Min Act: -0.0000

Data Index: 1483662 (The Pile)

Max Activating Token Index: 318

Text #12

Max Range: 1.2363. Min Range: -1.2363

Max Act: 0.8993. Min Act: -0.0000

Data Index: 1544007 (The Pile)

Max Activating Token Index: 378

Text #13

Max Range: 1.2363. Min Range: -1.2363

Max Act: 0.9310. Min Act: -0.0000

Data Index: 438105 (The Pile)

Max Activating Token Index: 162

Text #14

Max Range: 1.2363. Min Range: -1.2363

Max Act: 0.8376. Min Act: -0.0000

Data Index: 1867930 (The Pile)

Max Activating Token Index: 508

Text #15

Max Range: 1.2363. Min Range: -1.2363

Max Act: 0.8643. Min Act: -0.0000

Data Index: 1255758 (The Pile)

Max Activating Token Index: 849

Text #16

Max Range: 1.2363. Min Range: -1.2363

Max Act: 0.7549. Min Act: -0.0000

Data Index: 1169836 (The Pile)

Max Activating Token Index: 438

Text #17

Max Range: 1.2363. Min Range: -1.2363

Max Act: 0.8005. Min Act: -0.0000

Data Index: 559817 (The Pile)

Max Activating Token Index: 287

Text #18

Max Range: 1.2363. Min Range: -1.2363

Max Act: 0.8317. Min Act: -0.0000

Data Index: 1477934 (The Pile)

Max Activating Token Index: 650

Text #19

Max Range: 1.2363. Min Range: -1.2363

Max Act: 0.7616. Min Act: -0.0000

Data Index: 1204124 (The Pile)

Max Activating Token Index: 120