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

Dataset: The Pile

Neuron 2445 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: 0.9200. Min Range: -0.9200

Max Act: 0.8934. Min Act: -0.0000

Data Index: 1409195 (The Pile)

Max Activating Token Index: 273

Text #1

Max Range: 0.9200. Min Range: -0.9200

Max Act: 0.9200. Min Act: -0.0000

Data Index: 1862712 (The Pile)

Max Activating Token Index: 408

Text #2

Max Range: 0.9200. Min Range: -0.9200

Max Act: 0.8521. Min Act: -0.0000

Data Index: 883963 (The Pile)

Max Activating Token Index: 919

Text #3

Max Range: 0.9200. Min Range: -0.9200

Max Act: 0.7977. Min Act: -0.0000

Data Index: 1220529 (The Pile)

Max Activating Token Index: 341

Text #4

Max Range: 0.9200. Min Range: -0.9200

Max Act: 0.7361. Min Act: -0.0000

Data Index: 195410 (The Pile)

Max Activating Token Index: 517

Text #5

Max Range: 0.9200. Min Range: -0.9200

Max Act: 0.7755. Min Act: -0.0000

Data Index: 339949 (The Pile)

Max Activating Token Index: 831

Text #6

Max Range: 0.9200. Min Range: -0.9200

Max Act: 0.6270. Min Act: -0.0000

Data Index: 1256887 (The Pile)

Max Activating Token Index: 380

Text #7

Max Range: 0.9200. Min Range: -0.9200

Max Act: 0.6684. Min Act: -0.0000

Data Index: 1259126 (The Pile)

Max Activating Token Index: 362

Text #8

Max Range: 0.9200. Min Range: -0.9200

Max Act: 0.6567. Min Act: -0.0000

Data Index: 767338 (The Pile)

Max Activating Token Index: 937

Text #9

Max Range: 0.9200. Min Range: -0.9200

Max Act: 0.5777. Min Act: -0.0000

Data Index: 1827741 (The Pile)

Max Activating Token Index: 503

Text #10

Max Range: 0.9200. Min Range: -0.9200

Max Act: 0.5971. Min Act: -0.0000

Data Index: 1116184 (The Pile)

Max Activating Token Index: 856

Text #11

Max Range: 0.9200. Min Range: -0.9200

Max Act: 0.6340. Min Act: -0.0000

Data Index: 691276 (The Pile)

Max Activating Token Index: 522

Text #12

Max Range: 0.9200. Min Range: -0.9200

Max Act: 0.5993. Min Act: -0.0000

Data Index: 227676 (The Pile)

Max Activating Token Index: 851

Text #13

Max Range: 0.9200. Min Range: -0.9200

Max Act: 0.5873. Min Act: -0.0000

Data Index: 1618365 (The Pile)

Max Activating Token Index: 664

Text #14

Max Range: 0.9200. Min Range: -0.9200

Max Act: 0.6514. Min Act: -0.0000

Data Index: 1178224 (The Pile)

Max Activating Token Index: 1023

Text #15

Max Range: 0.9200. Min Range: -0.9200

Max Act: 0.5659. Min Act: -0.0000

Data Index: 456250 (The Pile)

Max Activating Token Index: 315

Text #16

Max Range: 0.9200. Min Range: -0.9200

Max Act: 0.5889. Min Act: -0.0000

Data Index: 1339292 (The Pile)

Max Activating Token Index: 1007

Text #17

Max Range: 0.9200. Min Range: -0.9200

Max Act: 0.5735. Min Act: -0.0000

Data Index: 1963893 (The Pile)

Max Activating Token Index: 78

Text #18

Max Range: 0.9200. Min Range: -0.9200

Max Act: 0.5402. Min Act: -0.0000

Data Index: 526602 (The Pile)

Max Activating Token Index: 322

Text #19

Max Range: 0.9200. Min Range: -0.9200

Max Act: 0.5559. Min Act: -0.0000

Data Index: 1465490 (The Pile)

Max Activating Token Index: 190