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

Dataset: The Pile

Neuron 1655 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: 10.1545. Min Range: -10.1545

Max Act: 10.1545. Min Act: -0.0000

Data Index: 1883945 (The Pile)

Max Activating Token Index: 378

Text #1

Max Range: 10.1545. Min Range: -10.1545

Max Act: 9.5497. Min Act: -0.0000

Data Index: 1999959 (The Pile)

Max Activating Token Index: 510

Text #2

Max Range: 10.1545. Min Range: -10.1545

Max Act: 9.2692. Min Act: -0.0000

Data Index: 1472434 (The Pile)

Max Activating Token Index: 428

Text #3

Max Range: 10.1545. Min Range: -10.1545

Max Act: 9.3167. Min Act: -0.0000

Data Index: 1820864 (The Pile)

Max Activating Token Index: 708

Text #4

Max Range: 10.1545. Min Range: -10.1545

Max Act: 9.5400. Min Act: -0.0000

Data Index: 96167 (The Pile)

Max Activating Token Index: 252

Text #5

Max Range: 10.1545. Min Range: -10.1545

Max Act: 9.1387. Min Act: -0.0000

Data Index: 418603 (The Pile)

Max Activating Token Index: 208

Text #6

Max Range: 10.1545. Min Range: -10.1545

Max Act: 8.5888. Min Act: -0.0000

Data Index: 1598396 (The Pile)

Max Activating Token Index: 166

Text #7

Max Range: 10.1545. Min Range: -10.1545

Max Act: 8.5935. Min Act: -0.0000

Data Index: 222652 (The Pile)

Max Activating Token Index: 103

Text #8

Max Range: 10.1545. Min Range: -10.1545

Max Act: 8.9166. Min Act: -0.0000

Data Index: 1456988 (The Pile)

Max Activating Token Index: 41

Text #9

Max Range: 10.1545. Min Range: -10.1545

Max Act: 8.1365. Min Act: -0.0000

Data Index: 1518860 (The Pile)

Max Activating Token Index: 356

Text #10

Max Range: 10.1545. Min Range: -10.1545

Max Act: 8.5691. Min Act: -0.0000

Data Index: 162370 (The Pile)

Max Activating Token Index: 243

Text #11

Max Range: 10.1545. Min Range: -10.1545

Max Act: 8.2971. Min Act: -0.0000

Data Index: 1664367 (The Pile)

Max Activating Token Index: 317

Text #12

Max Range: 10.1545. Min Range: -10.1545

Max Act: 9.0028. Min Act: -0.0000

Data Index: 1327992 (The Pile)

Max Activating Token Index: 297

Text #13

Max Range: 10.1545. Min Range: -10.1545

Max Act: 8.4622. Min Act: -0.0000

Data Index: 1436779 (The Pile)

Max Activating Token Index: 257

Text #14

Max Range: 10.1545. Min Range: -10.1545

Max Act: 8.3551. Min Act: -0.0000

Data Index: 1918606 (The Pile)

Max Activating Token Index: 675

Text #15

Max Range: 10.1545. Min Range: -10.1545

Max Act: 8.6582. Min Act: -0.0000

Data Index: 617280 (The Pile)

Max Activating Token Index: 134

Text #16

Max Range: 10.1545. Min Range: -10.1545

Max Act: 8.0968. Min Act: -0.0000

Data Index: 991921 (The Pile)

Max Activating Token Index: 248

Text #17

Max Range: 10.1545. Min Range: -10.1545

Max Act: 8.0739. Min Act: -0.0000

Data Index: 359483 (The Pile)

Max Activating Token Index: 49

Text #18

Max Range: 10.1545. Min Range: -10.1545

Max Act: 8.2224. Min Act: -0.0000

Data Index: 84856 (The Pile)

Max Activating Token Index: 971

Text #19

Max Range: 10.1545. Min Range: -10.1545

Max Act: 8.7067. Min Act: -0.0000

Data Index: 1508223 (The Pile)

Max Activating Token Index: 69