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

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

Neuron 2735 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: 0.1647. Min Range: -0.1647

Max Act: 0.1647. Min Act: -0.0001

Data Index: 550810 (C4 (Web Text))

Max Activating Token Index: 17

Text #1

Max Range: 0.1647. Min Range: -0.1647

Max Act: 0.1364. Min Act: -0.0001

Data Index: 501481 (C4 (Web Text))

Max Activating Token Index: 627

Text #2

Max Range: 0.1647. Min Range: -0.1647

Max Act: 0.1379. Min Act: -0.0001

Data Index: 1281644 (C4 (Web Text))

Max Activating Token Index: 116

Text #3

Max Range: 0.1647. Min Range: -0.1647

Max Act: 0.1281. Min Act: -0.0001

Data Index: 1124552 (C4 (Web Text))

Max Activating Token Index: 244

Text #4

Max Range: 0.1647. Min Range: -0.1647

Max Act: 0.1333. Min Act: -0.0001

Data Index: 999270 (C4 (Web Text))

Max Activating Token Index: 674

Text #5

Max Range: 0.1647. Min Range: -0.1647

Max Act: 0.1262. Min Act: -0.0001

Data Index: 670923 (C4 (Web Text))

Max Activating Token Index: 635

Text #6

Max Range: 0.1647. Min Range: -0.1647

Max Act: 0.1257. Min Act: -0.0001

Data Index: 721676 (C4 (Web Text))

Max Activating Token Index: 761

Text #7

Max Range: 0.1647. Min Range: -0.1647

Max Act: 0.1208. Min Act: -0.0001

Data Index: 900745 (C4 (Web Text))

Max Activating Token Index: 667

Text #8

Max Range: 0.1647. Min Range: -0.1647

Max Act: 0.1249. Min Act: -0.0001

Data Index: 748185 (C4 (Web Text))

Max Activating Token Index: 637

Text #9

Max Range: 0.1647. Min Range: -0.1647

Max Act: 0.1202. Min Act: -0.0001

Data Index: 8699 (C4 (Web Text))

Max Activating Token Index: 23

Text #10

Max Range: 0.1647. Min Range: -0.1647

Max Act: 0.1199. Min Act: -0.0000

Data Index: 841094 (C4 (Web Text))

Max Activating Token Index: 956

Text #11

Max Range: 0.1647. Min Range: -0.1647

Max Act: 0.1166. Min Act: -0.0001

Data Index: 702027 (C4 (Web Text))

Max Activating Token Index: 354

Text #12

Max Range: 0.1647. Min Range: -0.1647

Max Act: 0.1160. Min Act: 0.0000

Data Index: 365122 (C4 (Web Text))

Max Activating Token Index: 315

Text #13

Max Range: 0.1647. Min Range: -0.1647

Max Act: 0.1153. Min Act: -0.0001

Data Index: 936993 (C4 (Web Text))

Max Activating Token Index: 81

Text #14

Max Range: 0.1647. Min Range: -0.1647

Max Act: 0.1073. Min Act: -0.0001

Data Index: 1050399 (C4 (Web Text))

Max Activating Token Index: 40

Text #15

Max Range: 0.1647. Min Range: -0.1647

Max Act: 0.1072. Min Act: -0.0001

Data Index: 120711 (C4 (Web Text))

Max Activating Token Index: 216

Text #16

Max Range: 0.1647. Min Range: -0.1647

Max Act: 0.1097. Min Act: -0.0001

Data Index: 654033 (C4 (Web Text))

Max Activating Token Index: 28

Text #17

Max Range: 0.1647. Min Range: -0.1647

Max Act: 0.1067. Min Act: -0.0001

Data Index: 1093122 (C4 (Web Text))

Max Activating Token Index: 952

Text #18

Max Range: 0.1647. Min Range: -0.1647

Max Act: 0.1022. Min Act: -0.0001

Data Index: 23894 (C4 (Web Text))

Max Activating Token Index: 184

Text #19

Max Range: 0.1647. Min Range: -0.1647

Max Act: 0.1102. Min Act: -0.0001

Data Index: 843962 (C4 (Web Text))

Max Activating Token Index: 151