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

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

Neuron 3972 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.1178. Min Act: -0.0001

Data Index: 902691 (C4 (Web Text))

Max Activating Token Index: 869

Text #1

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.1082. Min Act: -0.0001

Data Index: 511944 (C4 (Web Text))

Max Activating Token Index: 146

Text #2

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.1030. Min Act: -0.0001

Data Index: 246378 (C4 (Web Text))

Max Activating Token Index: 923

Text #3

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.1021. Min Act: -0.0001

Data Index: 543643 (C4 (Web Text))

Max Activating Token Index: 537

Text #4

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.0985. Min Act: -0.0001

Data Index: 976260 (C4 (Web Text))

Max Activating Token Index: 509

Text #5

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.0974. Min Act: -0.0001

Data Index: 818392 (C4 (Web Text))

Max Activating Token Index: 134

Text #6

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.0973. Min Act: -0.0001

Data Index: 610364 (C4 (Web Text))

Max Activating Token Index: 745

Text #7

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.0960. Min Act: -0.0001

Data Index: 402304 (C4 (Web Text))

Max Activating Token Index: 808

Text #8

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.0996. Min Act: -0.0001

Data Index: 371444 (C4 (Web Text))

Max Activating Token Index: 315

Text #9

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.1023. Min Act: -0.0001

Data Index: 1351336 (C4 (Web Text))

Max Activating Token Index: 306

Text #10

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.0967. Min Act: -0.0001

Data Index: 1007169 (C4 (Web Text))

Max Activating Token Index: 996

Text #11

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.0982. Min Act: -0.0001

Data Index: 719328 (C4 (Web Text))

Max Activating Token Index: 920

Text #12

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.0937. Min Act: -0.0001

Data Index: 781072 (C4 (Web Text))

Max Activating Token Index: 203

Text #13

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.0969. Min Act: -0.0001

Data Index: 143546 (C4 (Web Text))

Max Activating Token Index: 16

Text #14

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.0833. Min Act: -0.0001

Data Index: 909914 (C4 (Web Text))

Max Activating Token Index: 891

Text #15

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.0897. Min Act: -0.0001

Data Index: 314178 (C4 (Web Text))

Max Activating Token Index: 49

Text #16

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.0854. Min Act: -0.0001

Data Index: 489377 (C4 (Web Text))

Max Activating Token Index: 620

Text #17

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.0887. Min Act: -0.0001

Data Index: 545509 (C4 (Web Text))

Max Activating Token Index: 379

Text #18

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.0846. Min Act: -0.0001

Data Index: 1267477 (C4 (Web Text))

Max Activating Token Index: 41

Text #19

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.0874. Min Act: -0.0001

Data Index: 729969 (C4 (Web Text))

Max Activating Token Index: 82