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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1023 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1928. Min Act: -0.0000

Data Index: 279785 (C4 (Web Text))

Max Activating Token Index: 25

Text #1

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1568. Min Act: -0.0000

Data Index: 679049 (C4 (Web Text))

Max Activating Token Index: 32

Text #2

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1556. Min Act: -0.0000

Data Index: 273003 (C4 (Web Text))

Max Activating Token Index: 233

Text #3

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1418. Min Act: -0.0000

Data Index: 710846 (C4 (Web Text))

Max Activating Token Index: 494

Text #4

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1422. Min Act: -0.0000

Data Index: 1102303 (C4 (Web Text))

Max Activating Token Index: 623

Text #5

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1343. Min Act: -0.0000

Data Index: 280957 (C4 (Web Text))

Max Activating Token Index: 502

Text #6

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1277. Min Act: -0.0000

Data Index: 615530 (C4 (Web Text))

Max Activating Token Index: 305

Text #7

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1311. Min Act: -0.0000

Data Index: 1327321 (C4 (Web Text))

Max Activating Token Index: 942

Text #8

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1247. Min Act: -0.0000

Data Index: 530743 (C4 (Web Text))

Max Activating Token Index: 362

Text #9

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1149. Min Act: -0.0000

Data Index: 209573 (C4 (Web Text))

Max Activating Token Index: 424

Text #10

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1200. Min Act: -0.0000

Data Index: 668145 (C4 (Web Text))

Max Activating Token Index: 145

Text #11

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1108. Min Act: -0.0000

Data Index: 904171 (C4 (Web Text))

Max Activating Token Index: 422

Text #12

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1107. Min Act: -0.0000

Data Index: 612823 (C4 (Web Text))

Max Activating Token Index: 643

Text #13

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1198. Min Act: -0.0000

Data Index: 203332 (C4 (Web Text))

Max Activating Token Index: 933

Text #14

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1124. Min Act: -0.0000

Data Index: 1030407 (C4 (Web Text))

Max Activating Token Index: 619

Text #15

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1103. Min Act: -0.0000

Data Index: 841000 (C4 (Web Text))

Max Activating Token Index: 849

Text #16

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1054. Min Act: -0.0000

Data Index: 340361 (C4 (Web Text))

Max Activating Token Index: 56

Text #17

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1055. Min Act: -0.0000

Data Index: 1261837 (C4 (Web Text))

Max Activating Token Index: 18

Text #18

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1082. Min Act: -0.0000

Data Index: 1009102 (C4 (Web Text))

Max Activating Token Index: 486

Text #19

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1123. Min Act: -0.0000

Data Index: 1337652 (C4 (Web Text))

Max Activating Token Index: 99