Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2926 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.2340. Min Act: -0.0000

Data Index: 40690 (The Pile)

Max Activating Token Index: 53

Text #1

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.2330. Min Act: -0.0000

Data Index: 170621 (The Pile)

Max Activating Token Index: 992

Text #2

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.2297. Min Act: -0.0000

Data Index: 1210186 (The Pile)

Max Activating Token Index: 537

Text #3

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.2125. Min Act: -0.0000

Data Index: 1394733 (The Pile)

Max Activating Token Index: 213

Text #4

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.2098. Min Act: -0.0000

Data Index: 742961 (The Pile)

Max Activating Token Index: 697

Text #5

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.2047. Min Act: -0.0000

Data Index: 1032310 (The Pile)

Max Activating Token Index: 975

Text #6

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.2161. Min Act: -0.0000

Data Index: 1412548 (The Pile)

Max Activating Token Index: 200

Text #7

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.2068. Min Act: -0.0000

Data Index: 1031854 (The Pile)

Max Activating Token Index: 805

Text #8

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.2055. Min Act: -0.0000

Data Index: 1723977 (The Pile)

Max Activating Token Index: 994

Text #9

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.2052. Min Act: -0.0000

Data Index: 933875 (The Pile)

Max Activating Token Index: 89

Text #10

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.2188. Min Act: -0.0000

Data Index: 182518 (The Pile)

Max Activating Token Index: 580

Text #11

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.2077. Min Act: -0.0000

Data Index: 1590050 (The Pile)

Max Activating Token Index: 370

Text #12

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.2060. Min Act: -0.0000

Data Index: 1964768 (The Pile)

Max Activating Token Index: 437

Text #13

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.2057. Min Act: -0.0000

Data Index: 805057 (The Pile)

Max Activating Token Index: 676

Text #14

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.1940. Min Act: -0.0000

Data Index: 209217 (The Pile)

Max Activating Token Index: 76

Text #15

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.2085. Min Act: -0.0000

Data Index: 1859858 (The Pile)

Max Activating Token Index: 698

Text #16

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.2004. Min Act: -0.0000

Data Index: 245828 (The Pile)

Max Activating Token Index: 402

Text #17

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.2098. Min Act: 0.0000

Data Index: 390955 (The Pile)

Max Activating Token Index: 897

Text #18

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.1936. Min Act: 0.0000

Data Index: 1851397 (The Pile)

Max Activating Token Index: 451

Text #19

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.1951. Min Act: -0.0000

Data Index: 1111115 (The Pile)

Max Activating Token Index: 79