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

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

Neuron 2910 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3695. Min Range: -1.3695

Max Act: 1.3569. Min Act: -0.0001

Data Index: 939073 (C4 (Web Text))

Max Activating Token Index: 947

Text #1

Max Range: 1.3695. Min Range: -1.3695

Max Act: 1.3695. Min Act: -0.0001

Data Index: 1089449 (C4 (Web Text))

Max Activating Token Index: 304

Text #2

Max Range: 1.3695. Min Range: -1.3695

Max Act: 1.2981. Min Act: -0.0001

Data Index: 954090 (C4 (Web Text))

Max Activating Token Index: 673

Text #3

Max Range: 1.3695. Min Range: -1.3695

Max Act: 1.2566. Min Act: -0.0001

Data Index: 687246 (C4 (Web Text))

Max Activating Token Index: 45

Text #4

Max Range: 1.3695. Min Range: -1.3695

Max Act: 1.2737. Min Act: -0.0001

Data Index: 145283 (C4 (Web Text))

Max Activating Token Index: 291

Text #5

Max Range: 1.3695. Min Range: -1.3695

Max Act: 1.2136. Min Act: -0.0001

Data Index: 348769 (C4 (Web Text))

Max Activating Token Index: 544

Text #6

Max Range: 1.3695. Min Range: -1.3695

Max Act: 1.1800. Min Act: -0.0001

Data Index: 850858 (C4 (Web Text))

Max Activating Token Index: 146

Text #7

Max Range: 1.3695. Min Range: -1.3695

Max Act: 1.1836. Min Act: -0.0001

Data Index: 448900 (C4 (Web Text))

Max Activating Token Index: 144

Text #8

Max Range: 1.3695. Min Range: -1.3695

Max Act: 1.2215. Min Act: -0.0001

Data Index: 1357682 (C4 (Web Text))

Max Activating Token Index: 89

Text #9

Max Range: 1.3695. Min Range: -1.3695

Max Act: 1.1673. Min Act: -0.0001

Data Index: 231270 (C4 (Web Text))

Max Activating Token Index: 206

Text #10

Max Range: 1.3695. Min Range: -1.3695

Max Act: 1.1852. Min Act: -0.0001

Data Index: 660204 (C4 (Web Text))

Max Activating Token Index: 104

Text #11

Max Range: 1.3695. Min Range: -1.3695

Max Act: 1.0685. Min Act: -0.0001

Data Index: 808980 (C4 (Web Text))

Max Activating Token Index: 223

Text #12

Max Range: 1.3695. Min Range: -1.3695

Max Act: 1.1400. Min Act: -0.0001

Data Index: 370355 (C4 (Web Text))

Max Activating Token Index: 852

Text #13

Max Range: 1.3695. Min Range: -1.3695

Max Act: 1.0942. Min Act: -0.0001

Data Index: 387237 (C4 (Web Text))

Max Activating Token Index: 224

Text #14

Max Range: 1.3695. Min Range: -1.3695

Max Act: 1.0721. Min Act: -0.0001

Data Index: 1228939 (C4 (Web Text))

Max Activating Token Index: 691

Text #15

Max Range: 1.3695. Min Range: -1.3695

Max Act: 1.0549. Min Act: -0.0001

Data Index: 1201634 (C4 (Web Text))

Max Activating Token Index: 824

Text #16

Max Range: 1.3695. Min Range: -1.3695

Max Act: 1.1018. Min Act: -0.0001

Data Index: 815985 (C4 (Web Text))

Max Activating Token Index: 80

Text #17

Max Range: 1.3695. Min Range: -1.3695

Max Act: 1.1023. Min Act: -0.0001

Data Index: 931008 (C4 (Web Text))

Max Activating Token Index: 221

Text #18

Max Range: 1.3695. Min Range: -1.3695

Max Act: 1.1183. Min Act: -0.0001

Data Index: 488979 (C4 (Web Text))

Max Activating Token Index: 361

Text #19

Max Range: 1.3695. Min Range: -1.3695

Max Act: 1.0123. Min Act: -0.0001

Data Index: 9469 (C4 (Web Text))

Max Activating Token Index: 801