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

Dataset: The Pile

Neuron 2685 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1430. Min Range: -0.1430

Max Act: 0.1283. Min Act: -0.0000

Data Index: 346281 (The Pile)

Max Activating Token Index: 833

Text #1

Max Range: 0.1430. Min Range: -0.1430

Max Act: 0.1430. Min Act: -0.0000

Data Index: 139771 (The Pile)

Max Activating Token Index: 714

Text #2

Max Range: 0.1430. Min Range: -0.1430

Max Act: 0.1367. Min Act: -0.0000

Data Index: 1963881 (The Pile)

Max Activating Token Index: 406

Text #3

Max Range: 0.1430. Min Range: -0.1430

Max Act: 0.1096. Min Act: -0.0000

Data Index: 1422472 (The Pile)

Max Activating Token Index: 801

Text #4

Max Range: 0.1430. Min Range: -0.1430

Max Act: 0.1019. Min Act: -0.0000

Data Index: 1072334 (The Pile)

Max Activating Token Index: 824

Text #5

Max Range: 0.1430. Min Range: -0.1430

Max Act: 0.1054. Min Act: -0.0000

Data Index: 63290 (The Pile)

Max Activating Token Index: 991

Text #6

Max Range: 0.1430. Min Range: -0.1430

Max Act: 0.1078. Min Act: -0.0000

Data Index: 296947 (The Pile)

Max Activating Token Index: 316

Text #7

Max Range: 0.1430. Min Range: -0.1430

Max Act: 0.1040. Min Act: -0.0000

Data Index: 737278 (The Pile)

Max Activating Token Index: 644

Text #8

Max Range: 0.1430. Min Range: -0.1430

Max Act: 0.1060. Min Act: -0.0000

Data Index: 1929905 (The Pile)

Max Activating Token Index: 882

Text #9

Max Range: 0.1430. Min Range: -0.1430

Max Act: 0.0941. Min Act: -0.0000

Data Index: 1933397 (The Pile)

Max Activating Token Index: 90

Text #10

Max Range: 0.1430. Min Range: -0.1430

Max Act: 0.1148. Min Act: -0.0000

Data Index: 1171771 (The Pile)

Max Activating Token Index: 194

Text #11

Max Range: 0.1430. Min Range: -0.1430

Max Act: 0.0829. Min Act: -0.0000

Data Index: 1940230 (The Pile)

Max Activating Token Index: 180

Text #12

Max Range: 0.1430. Min Range: -0.1430

Max Act: 0.0884. Min Act: -0.0000

Data Index: 201288 (The Pile)

Max Activating Token Index: 50

Text #13

Max Range: 0.1430. Min Range: -0.1430

Max Act: 0.0956. Min Act: -0.0000

Data Index: 239716 (The Pile)

Max Activating Token Index: 524

Text #14

Max Range: 0.1430. Min Range: -0.1430

Max Act: 0.0832. Min Act: -0.0000

Data Index: 971424 (The Pile)

Max Activating Token Index: 978

Text #15

Max Range: 0.1430. Min Range: -0.1430

Max Act: 0.0879. Min Act: -0.0000

Data Index: 650542 (The Pile)

Max Activating Token Index: 1003

Text #16

Max Range: 0.1430. Min Range: -0.1430

Max Act: 0.0779. Min Act: -0.0000

Data Index: 194906 (The Pile)

Max Activating Token Index: 69

Text #17

Max Range: 0.1430. Min Range: -0.1430

Max Act: 0.0769. Min Act: -0.0000

Data Index: 1810706 (The Pile)

Max Activating Token Index: 833

Text #18

Max Range: 0.1430. Min Range: -0.1430

Max Act: 0.0880. Min Act: -0.0000

Data Index: 1662015 (The Pile)

Max Activating Token Index: 633

Text #19

Max Range: 0.1430. Min Range: -0.1430

Max Act: 0.0836. Min Act: -0.0000

Data Index: 779049 (The Pile)

Max Activating Token Index: 647