Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3460 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1641. Min Range: -0.1641

Max Act: 0.1641. Min Act: -0.0001

Data Index: 812725 (C4 (Web Text))

Max Activating Token Index: 627

Text #1

Max Range: 0.1641. Min Range: -0.1641

Max Act: 0.1570. Min Act: -0.0001

Data Index: 370407 (C4 (Web Text))

Max Activating Token Index: 768

Text #2

Max Range: 0.1641. Min Range: -0.1641

Max Act: 0.1435. Min Act: -0.0001

Data Index: 88673 (C4 (Web Text))

Max Activating Token Index: 859

Text #3

Max Range: 0.1641. Min Range: -0.1641

Max Act: 0.1493. Min Act: -0.0001

Data Index: 50047 (C4 (Web Text))

Max Activating Token Index: 528

Text #4

Max Range: 0.1641. Min Range: -0.1641

Max Act: 0.1430. Min Act: -0.0001

Data Index: 460089 (C4 (Web Text))

Max Activating Token Index: 862

Text #5

Max Range: 0.1641. Min Range: -0.1641

Max Act: 0.1377. Min Act: -0.0001

Data Index: 1227144 (C4 (Web Text))

Max Activating Token Index: 216

Text #6

Max Range: 0.1641. Min Range: -0.1641

Max Act: 0.1183. Min Act: -0.0001

Data Index: 1046496 (C4 (Web Text))

Max Activating Token Index: 59

Text #7

Max Range: 0.1641. Min Range: -0.1641

Max Act: 0.1228. Min Act: -0.0001

Data Index: 146569 (C4 (Web Text))

Max Activating Token Index: 809

Text #8

Max Range: 0.1641. Min Range: -0.1641

Max Act: 0.1152. Min Act: -0.0001

Data Index: 1300454 (C4 (Web Text))

Max Activating Token Index: 29

Text #9

Max Range: 0.1641. Min Range: -0.1641

Max Act: 0.1119. Min Act: -0.0001

Data Index: 224896 (C4 (Web Text))

Max Activating Token Index: 997

Text #10

Max Range: 0.1641. Min Range: -0.1641

Max Act: 0.1118. Min Act: -0.0001

Data Index: 1282890 (C4 (Web Text))

Max Activating Token Index: 282

Text #11

Max Range: 0.1641. Min Range: -0.1641

Max Act: 0.1108. Min Act: -0.0001

Data Index: 799090 (C4 (Web Text))

Max Activating Token Index: 94

Text #12

Max Range: 0.1641. Min Range: -0.1641

Max Act: 0.1098. Min Act: -0.0001

Data Index: 864000 (C4 (Web Text))

Max Activating Token Index: 442

Text #13

Max Range: 0.1641. Min Range: -0.1641

Max Act: 0.1139. Min Act: -0.0001

Data Index: 1341447 (C4 (Web Text))

Max Activating Token Index: 898

Text #14

Max Range: 0.1641. Min Range: -0.1641

Max Act: 0.0937. Min Act: -0.0001

Data Index: 235272 (C4 (Web Text))

Max Activating Token Index: 804

Text #15

Max Range: 0.1641. Min Range: -0.1641

Max Act: 0.1048. Min Act: -0.0001

Data Index: 530584 (C4 (Web Text))

Max Activating Token Index: 844

Text #16

Max Range: 0.1641. Min Range: -0.1641

Max Act: 0.1075. Min Act: -0.0001

Data Index: 451761 (C4 (Web Text))

Max Activating Token Index: 916

Text #17

Max Range: 0.1641. Min Range: -0.1641

Max Act: 0.1032. Min Act: -0.0001

Data Index: 1010213 (C4 (Web Text))

Max Activating Token Index: 459

Text #18

Max Range: 0.1641. Min Range: -0.1641

Max Act: 0.1017. Min Act: -0.0001

Data Index: 100017 (C4 (Web Text))

Max Activating Token Index: 128

Text #19

Max Range: 0.1641. Min Range: -0.1641

Max Act: 0.1052. Min Act: -0.0001

Data Index: 732364 (C4 (Web Text))

Max Activating Token Index: 693