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

Dataset: The Pile

Neuron 338 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: 0.2715. Min Range: -0.2715

Max Act: 0.2715. Min Act: -0.0000

Data Index: 879506 (The Pile)

Max Activating Token Index: 671

Text #1

Max Range: 0.2715. Min Range: -0.2715

Max Act: 0.2578. Min Act: -0.0000

Data Index: 1519724 (The Pile)

Max Activating Token Index: 767

Text #2

Max Range: 0.2715. Min Range: -0.2715

Max Act: 0.2228. Min Act: -0.0000

Data Index: 343222 (The Pile)

Max Activating Token Index: 318

Text #3

Max Range: 0.2715. Min Range: -0.2715

Max Act: 0.2468. Min Act: -0.0000

Data Index: 208058 (The Pile)

Max Activating Token Index: 941

Text #4

Max Range: 0.2715. Min Range: -0.2715

Max Act: 0.2290. Min Act: -0.0000

Data Index: 1327652 (The Pile)

Max Activating Token Index: 439

Text #5

Max Range: 0.2715. Min Range: -0.2715

Max Act: 0.2253. Min Act: -0.0000

Data Index: 1891342 (The Pile)

Max Activating Token Index: 384

Text #6

Max Range: 0.2715. Min Range: -0.2715

Max Act: 0.2107. Min Act: -0.0000

Data Index: 214812 (The Pile)

Max Activating Token Index: 814

Text #7

Max Range: 0.2715. Min Range: -0.2715

Max Act: 0.2011. Min Act: -0.0000

Data Index: 844343 (The Pile)

Max Activating Token Index: 401

Text #8

Max Range: 0.2715. Min Range: -0.2715

Max Act: 0.1643. Min Act: -0.0000

Data Index: 1873455 (The Pile)

Max Activating Token Index: 225

Text #9

Max Range: 0.2715. Min Range: -0.2715

Max Act: 0.2010. Min Act: -0.0000

Data Index: 1391410 (The Pile)

Max Activating Token Index: 141

Text #10

Max Range: 0.2715. Min Range: -0.2715

Max Act: 0.2022. Min Act: -0.0000

Data Index: 774331 (The Pile)

Max Activating Token Index: 142

Text #11

Max Range: 0.2715. Min Range: -0.2715

Max Act: 0.1919. Min Act: -0.0000

Data Index: 1072070 (The Pile)

Max Activating Token Index: 503

Text #12

Max Range: 0.2715. Min Range: -0.2715

Max Act: 0.1888. Min Act: -0.0000

Data Index: 1156040 (The Pile)

Max Activating Token Index: 988

Text #13

Max Range: 0.2715. Min Range: -0.2715

Max Act: 0.1944. Min Act: -0.0000

Data Index: 1182302 (The Pile)

Max Activating Token Index: 353

Text #14

Max Range: 0.2715. Min Range: -0.2715

Max Act: 0.1911. Min Act: -0.0000

Data Index: 466320 (The Pile)

Max Activating Token Index: 229

Text #15

Max Range: 0.2715. Min Range: -0.2715

Max Act: 0.1676. Min Act: -0.0000

Data Index: 1120941 (The Pile)

Max Activating Token Index: 229

Text #16

Max Range: 0.2715. Min Range: -0.2715

Max Act: 0.1552. Min Act: -0.0000

Data Index: 346868 (The Pile)

Max Activating Token Index: 158

Text #17

Max Range: 0.2715. Min Range: -0.2715

Max Act: 0.1741. Min Act: -0.0000

Data Index: 199310 (The Pile)

Max Activating Token Index: 669

Text #18

Max Range: 0.2715. Min Range: -0.2715

Max Act: 0.1758. Min Act: 0.0000

Data Index: 994947 (The Pile)

Max Activating Token Index: 157

Text #19

Max Range: 0.2715. Min Range: -0.2715

Max Act: 0.1874. Min Act: -0.0000

Data Index: 1437221 (The Pile)

Max Activating Token Index: 634