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

Dataset: The Pile

Neuron 4833 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.2645. Min Act: -0.0000

Data Index: 476046 (The Pile)

Max Activating Token Index: 309

Text #1

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.2229. Min Act: -0.0000

Data Index: 532138 (The Pile)

Max Activating Token Index: 894

Text #2

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.2391. Min Act: -0.0000

Data Index: 939997 (The Pile)

Max Activating Token Index: 815

Text #3

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.2093. Min Act: -0.0000

Data Index: 135395 (The Pile)

Max Activating Token Index: 591

Text #4

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.2244. Min Act: -0.0000

Data Index: 1940157 (The Pile)

Max Activating Token Index: 249

Text #5

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.2200. Min Act: -0.0000

Data Index: 1172758 (The Pile)

Max Activating Token Index: 297

Text #6

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.2058. Min Act: -0.0000

Data Index: 619490 (The Pile)

Max Activating Token Index: 308

Text #7

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.2074. Min Act: -0.0000

Data Index: 1538596 (The Pile)

Max Activating Token Index: 426

Text #8

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.2164. Min Act: -0.0000

Data Index: 1271181 (The Pile)

Max Activating Token Index: 614

Text #9

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.1908. Min Act: -0.0000

Data Index: 1473959 (The Pile)

Max Activating Token Index: 429

Text #10

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.2033. Min Act: -0.0000

Data Index: 1159228 (The Pile)

Max Activating Token Index: 692

Text #11

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.1956. Min Act: -0.0000

Data Index: 1576864 (The Pile)

Max Activating Token Index: 329

Text #12

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.1887. Min Act: -0.0000

Data Index: 943867 (The Pile)

Max Activating Token Index: 243

Text #13

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.1828. Min Act: -0.0000

Data Index: 488326 (The Pile)

Max Activating Token Index: 627

Text #14

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.1731. Min Act: -0.0000

Data Index: 451967 (The Pile)

Max Activating Token Index: 1016

Text #15

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.1812. Min Act: -0.0000

Data Index: 1679027 (The Pile)

Max Activating Token Index: 857

Text #16

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.1938. Min Act: -0.0000

Data Index: 1071289 (The Pile)

Max Activating Token Index: 690

Text #17

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.1799. Min Act: -0.0000

Data Index: 1586590 (The Pile)

Max Activating Token Index: 554

Text #18

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.1911. Min Act: -0.0000

Data Index: 1806463 (The Pile)

Max Activating Token Index: 229

Text #19

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.1911. Min Act: -0.0000

Data Index: 1302621 (The Pile)

Max Activating Token Index: 749