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

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

Neuron 3149 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: 0.1147. Min Range: -0.1147

Max Act: 0.1147. Min Act: -0.0001

Data Index: 935275 (C4 (Web Text))

Max Activating Token Index: 479

Text #1

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.1068. Min Act: -0.0001

Data Index: 662031 (C4 (Web Text))

Max Activating Token Index: 983

Text #2

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.1040. Min Act: -0.0001

Data Index: 268549 (C4 (Web Text))

Max Activating Token Index: 760

Text #3

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.1110. Min Act: -0.0001

Data Index: 143141 (C4 (Web Text))

Max Activating Token Index: 621

Text #4

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.1050. Min Act: -0.0001

Data Index: 855771 (C4 (Web Text))

Max Activating Token Index: 390

Text #5

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.1113. Min Act: -0.0001

Data Index: 1229579 (C4 (Web Text))

Max Activating Token Index: 528

Text #6

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.1073. Min Act: -0.0001

Data Index: 1149972 (C4 (Web Text))

Max Activating Token Index: 276

Text #7

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.1046. Min Act: -0.0001

Data Index: 943295 (C4 (Web Text))

Max Activating Token Index: 803

Text #8

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.1075. Min Act: -0.0001

Data Index: 11844 (C4 (Web Text))

Max Activating Token Index: 987

Text #9

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.0903. Min Act: -0.0001

Data Index: 1034913 (C4 (Web Text))

Max Activating Token Index: 125

Text #10

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.0965. Min Act: -0.0001

Data Index: 1251335 (C4 (Web Text))

Max Activating Token Index: 260

Text #11

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.1027. Min Act: -0.0001

Data Index: 26546 (C4 (Web Text))

Max Activating Token Index: 505

Text #12

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.0959. Min Act: -0.0001

Data Index: 981286 (C4 (Web Text))

Max Activating Token Index: 505

Text #13

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.0946. Min Act: -0.0001

Data Index: 1098372 (C4 (Web Text))

Max Activating Token Index: 980

Text #14

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.0980. Min Act: -0.0001

Data Index: 375416 (C4 (Web Text))

Max Activating Token Index: 627

Text #15

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.0986. Min Act: -0.0001

Data Index: 273357 (C4 (Web Text))

Max Activating Token Index: 401

Text #16

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.1085. Min Act: -0.0001

Data Index: 814516 (C4 (Web Text))

Max Activating Token Index: 623

Text #17

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.0981. Min Act: -0.0001

Data Index: 799917 (C4 (Web Text))

Max Activating Token Index: 495

Text #18

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.0902. Min Act: -0.0001

Data Index: 218648 (C4 (Web Text))

Max Activating Token Index: 274

Text #19

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.0970. Min Act: -0.0001

Data Index: 61583 (C4 (Web Text))

Max Activating Token Index: 162