Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2254 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1502. Min Range: -0.1502

Max Act: 0.1502. Min Act: -0.0001

Data Index: 261787 (C4 (Web Text))

Max Activating Token Index: 13

Text #1

Max Range: 0.1502. Min Range: -0.1502

Max Act: 0.1305. Min Act: -0.0001

Data Index: 86429 (C4 (Web Text))

Max Activating Token Index: 9

Text #2

Max Range: 0.1502. Min Range: -0.1502

Max Act: 0.1163. Min Act: -0.0001

Data Index: 180039 (C4 (Web Text))

Max Activating Token Index: 689

Text #3

Max Range: 0.1502. Min Range: -0.1502

Max Act: 0.1111. Min Act: -0.0001

Data Index: 148737 (C4 (Web Text))

Max Activating Token Index: 361

Text #4

Max Range: 0.1502. Min Range: -0.1502

Max Act: 0.1090. Min Act: -0.0001

Data Index: 247091 (C4 (Web Text))

Max Activating Token Index: 412

Text #5

Max Range: 0.1502. Min Range: -0.1502

Max Act: 0.1130. Min Act: -0.0001

Data Index: 595243 (C4 (Web Text))

Max Activating Token Index: 685

Text #6

Max Range: 0.1502. Min Range: -0.1502

Max Act: 0.1114. Min Act: -0.0001

Data Index: 748279 (C4 (Web Text))

Max Activating Token Index: 53

Text #7

Max Range: 0.1502. Min Range: -0.1502

Max Act: 0.1088. Min Act: -0.0001

Data Index: 619463 (C4 (Web Text))

Max Activating Token Index: 456

Text #8

Max Range: 0.1502. Min Range: -0.1502

Max Act: 0.1048. Min Act: -0.0001

Data Index: 1164249 (C4 (Web Text))

Max Activating Token Index: 313

Text #9

Max Range: 0.1502. Min Range: -0.1502

Max Act: 0.1118. Min Act: -0.0001

Data Index: 323813 (C4 (Web Text))

Max Activating Token Index: 440

Text #10

Max Range: 0.1502. Min Range: -0.1502

Max Act: 0.0997. Min Act: -0.0001

Data Index: 278601 (C4 (Web Text))

Max Activating Token Index: 362

Text #11

Max Range: 0.1502. Min Range: -0.1502

Max Act: 0.1085. Min Act: -0.0001

Data Index: 496792 (C4 (Web Text))

Max Activating Token Index: 829

Text #12

Max Range: 0.1502. Min Range: -0.1502

Max Act: 0.1061. Min Act: -0.0001

Data Index: 576050 (C4 (Web Text))

Max Activating Token Index: 904

Text #13

Max Range: 0.1502. Min Range: -0.1502

Max Act: 0.1082. Min Act: -0.0001

Data Index: 51768 (C4 (Web Text))

Max Activating Token Index: 57

Text #14

Max Range: 0.1502. Min Range: -0.1502

Max Act: 0.1028. Min Act: -0.0001

Data Index: 147046 (C4 (Web Text))

Max Activating Token Index: 50

Text #15

Max Range: 0.1502. Min Range: -0.1502

Max Act: 0.1006. Min Act: -0.0001

Data Index: 943495 (C4 (Web Text))

Max Activating Token Index: 711

Text #16

Max Range: 0.1502. Min Range: -0.1502

Max Act: 0.1023. Min Act: -0.0001

Data Index: 298971 (C4 (Web Text))

Max Activating Token Index: 373

Text #17

Max Range: 0.1502. Min Range: -0.1502

Max Act: 0.0953. Min Act: -0.0001

Data Index: 1220614 (C4 (Web Text))

Max Activating Token Index: 261

Text #18

Max Range: 0.1502. Min Range: -0.1502

Max Act: 0.0912. Min Act: -0.0001

Data Index: 163834 (C4 (Web Text))

Max Activating Token Index: 602

Text #19

Max Range: 0.1502. Min Range: -0.1502

Max Act: 0.0976. Min Act: -0.0001

Data Index: 1181340 (C4 (Web Text))

Max Activating Token Index: 518