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

Dataset: The Pile

Neuron 620 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: 0.7805. Min Range: -0.7805

Max Act: 0.7340. Min Act: -0.0000

Data Index: 729527 (The Pile)

Max Activating Token Index: 397

Text #1

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.7805. Min Act: -0.0000

Data Index: 1350432 (The Pile)

Max Activating Token Index: 189

Text #2

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.7207. Min Act: -0.0000

Data Index: 1857814 (The Pile)

Max Activating Token Index: 915

Text #3

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.6279. Min Act: -0.0000

Data Index: 39446 (The Pile)

Max Activating Token Index: 653

Text #4

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.6491. Min Act: -0.0000

Data Index: 1377444 (The Pile)

Max Activating Token Index: 530

Text #5

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.6669. Min Act: -0.0000

Data Index: 1227062 (The Pile)

Max Activating Token Index: 66

Text #6

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.6854. Min Act: -0.0000

Data Index: 597459 (The Pile)

Max Activating Token Index: 927

Text #7

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.6154. Min Act: -0.0000

Data Index: 1044056 (The Pile)

Max Activating Token Index: 279

Text #8

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.6298. Min Act: -0.0000

Data Index: 1467758 (The Pile)

Max Activating Token Index: 257

Text #9

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.6725. Min Act: -0.0000

Data Index: 323763 (The Pile)

Max Activating Token Index: 599

Text #10

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.6019. Min Act: -0.0000

Data Index: 473870 (The Pile)

Max Activating Token Index: 160

Text #11

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.6595. Min Act: -0.0000

Data Index: 1930105 (The Pile)

Max Activating Token Index: 211

Text #12

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.6308. Min Act: -0.0000

Data Index: 1722581 (The Pile)

Max Activating Token Index: 502

Text #13

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.6309. Min Act: -0.0000

Data Index: 1183801 (The Pile)

Max Activating Token Index: 449

Text #14

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.6257. Min Act: -0.0000

Data Index: 1678563 (The Pile)

Max Activating Token Index: 38

Text #15

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.6389. Min Act: -0.0000

Data Index: 1381008 (The Pile)

Max Activating Token Index: 504

Text #16

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.6370. Min Act: -0.0000

Data Index: 1798867 (The Pile)

Max Activating Token Index: 310

Text #17

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.6086. Min Act: -0.0000

Data Index: 861075 (The Pile)

Max Activating Token Index: 224

Text #18

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.5633. Min Act: -0.0000

Data Index: 1292105 (The Pile)

Max Activating Token Index: 375

Text #19

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.6138. Min Act: -0.0000

Data Index: 376509 (The Pile)

Max Activating Token Index: 238