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

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

Neuron 854 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1344. Min Range: -0.1344

Max Act: 0.1338. Min Act: -0.0001

Data Index: 871726 (C4 (Web Text))

Max Activating Token Index: 232

Text #1

Max Range: 0.1344. Min Range: -0.1344

Max Act: 0.1344. Min Act: -0.0001

Data Index: 970038 (C4 (Web Text))

Max Activating Token Index: 730

Text #2

Max Range: 0.1344. Min Range: -0.1344

Max Act: 0.1272. Min Act: -0.0001

Data Index: 1070169 (C4 (Web Text))

Max Activating Token Index: 970

Text #3

Max Range: 0.1344. Min Range: -0.1344

Max Act: 0.1187. Min Act: -0.0001

Data Index: 390495 (C4 (Web Text))

Max Activating Token Index: 658

Text #4

Max Range: 0.1344. Min Range: -0.1344

Max Act: 0.1165. Min Act: -0.0001

Data Index: 543295 (C4 (Web Text))

Max Activating Token Index: 25

Text #5

Max Range: 0.1344. Min Range: -0.1344

Max Act: 0.1122. Min Act: -0.0001

Data Index: 958034 (C4 (Web Text))

Max Activating Token Index: 512

Text #6

Max Range: 0.1344. Min Range: -0.1344

Max Act: 0.1060. Min Act: -0.0001

Data Index: 1042516 (C4 (Web Text))

Max Activating Token Index: 957

Text #7

Max Range: 0.1344. Min Range: -0.1344

Max Act: 0.1130. Min Act: -0.0001

Data Index: 887112 (C4 (Web Text))

Max Activating Token Index: 634

Text #8

Max Range: 0.1344. Min Range: -0.1344

Max Act: 0.1150. Min Act: -0.0001

Data Index: 403306 (C4 (Web Text))

Max Activating Token Index: 22

Text #9

Max Range: 0.1344. Min Range: -0.1344

Max Act: 0.1070. Min Act: -0.0001

Data Index: 725692 (C4 (Web Text))

Max Activating Token Index: 559

Text #10

Max Range: 0.1344. Min Range: -0.1344

Max Act: 0.1078. Min Act: -0.0001

Data Index: 1318615 (C4 (Web Text))

Max Activating Token Index: 739

Text #11

Max Range: 0.1344. Min Range: -0.1344

Max Act: 0.1023. Min Act: -0.0001

Data Index: 1202621 (C4 (Web Text))

Max Activating Token Index: 107

Text #12

Max Range: 0.1344. Min Range: -0.1344

Max Act: 0.1016. Min Act: -0.0001

Data Index: 407658 (C4 (Web Text))

Max Activating Token Index: 647

Text #13

Max Range: 0.1344. Min Range: -0.1344

Max Act: 0.1005. Min Act: -0.0001

Data Index: 348586 (C4 (Web Text))

Max Activating Token Index: 17

Text #14

Max Range: 0.1344. Min Range: -0.1344

Max Act: 0.1065. Min Act: -0.0001

Data Index: 466680 (C4 (Web Text))

Max Activating Token Index: 21

Text #15

Max Range: 0.1344. Min Range: -0.1344

Max Act: 0.0987. Min Act: -0.0001

Data Index: 1231855 (C4 (Web Text))

Max Activating Token Index: 766

Text #16

Max Range: 0.1344. Min Range: -0.1344

Max Act: 0.1043. Min Act: -0.0001

Data Index: 277524 (C4 (Web Text))

Max Activating Token Index: 972

Text #17

Max Range: 0.1344. Min Range: -0.1344

Max Act: 0.0899. Min Act: -0.0001

Data Index: 1130150 (C4 (Web Text))

Max Activating Token Index: 876

Text #18

Max Range: 0.1344. Min Range: -0.1344

Max Act: 0.1090. Min Act: -0.0001

Data Index: 1318824 (C4 (Web Text))

Max Activating Token Index: 312

Text #19

Max Range: 0.1344. Min Range: -0.1344

Max Act: 0.0851. Min Act: -0.0001

Data Index: 1236104 (C4 (Web Text))

Max Activating Token Index: 26