Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1618 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.5565. Min Range: -1.5565

Max Act: 1.5565. Min Act: -0.0001

Data Index: 360138 (C4 (Web Text))

Max Activating Token Index: 272

Text #1

Max Range: 1.5565. Min Range: -1.5565

Max Act: 1.4066. Min Act: -0.0001

Data Index: 85089 (C4 (Web Text))

Max Activating Token Index: 118

Text #2

Max Range: 1.5565. Min Range: -1.5565

Max Act: 1.2563. Min Act: -0.0001

Data Index: 665617 (C4 (Web Text))

Max Activating Token Index: 8

Text #3

Max Range: 1.5565. Min Range: -1.5565

Max Act: 1.1946. Min Act: -0.0001

Data Index: 1359816 (C4 (Web Text))

Max Activating Token Index: 480

Text #4

Max Range: 1.5565. Min Range: -1.5565

Max Act: 1.2194. Min Act: -0.0001

Data Index: 1125551 (C4 (Web Text))

Max Activating Token Index: 232

Text #5

Max Range: 1.5565. Min Range: -1.5565

Max Act: 1.1774. Min Act: -0.0001

Data Index: 631367 (C4 (Web Text))

Max Activating Token Index: 859

Text #6

Max Range: 1.5565. Min Range: -1.5565

Max Act: 1.1058. Min Act: -0.0001

Data Index: 1160945 (C4 (Web Text))

Max Activating Token Index: 173

Text #7

Max Range: 1.5565. Min Range: -1.5565

Max Act: 1.0251. Min Act: -0.0001

Data Index: 343802 (C4 (Web Text))

Max Activating Token Index: 140

Text #8

Max Range: 1.5565. Min Range: -1.5565

Max Act: 1.0998. Min Act: -0.0001

Data Index: 1137729 (C4 (Web Text))

Max Activating Token Index: 669

Text #9

Max Range: 1.5565. Min Range: -1.5565

Max Act: 0.9733. Min Act: -0.0001

Data Index: 289866 (C4 (Web Text))

Max Activating Token Index: 105

Text #10

Max Range: 1.5565. Min Range: -1.5565

Max Act: 0.9925. Min Act: -0.0001

Data Index: 672210 (C4 (Web Text))

Max Activating Token Index: 375

Text #11

Max Range: 1.5565. Min Range: -1.5565

Max Act: 0.9569. Min Act: -0.0001

Data Index: 223162 (C4 (Web Text))

Max Activating Token Index: 637

Text #12

Max Range: 1.5565. Min Range: -1.5565

Max Act: 0.9587. Min Act: -0.0001

Data Index: 256550 (C4 (Web Text))

Max Activating Token Index: 125

Text #13

Max Range: 1.5565. Min Range: -1.5565

Max Act: 0.9752. Min Act: -0.0002

Data Index: 1065198 (C4 (Web Text))

Max Activating Token Index: 22

Text #14

Max Range: 1.5565. Min Range: -1.5565

Max Act: 1.0019. Min Act: -0.0001

Data Index: 287899 (C4 (Web Text))

Max Activating Token Index: 883

Text #15

Max Range: 1.5565. Min Range: -1.5565

Max Act: 0.9448. Min Act: -0.0001

Data Index: 1329941 (C4 (Web Text))

Max Activating Token Index: 279

Text #16

Max Range: 1.5565. Min Range: -1.5565

Max Act: 0.9201. Min Act: -0.0001

Data Index: 892615 (C4 (Web Text))

Max Activating Token Index: 364

Text #17

Max Range: 1.5565. Min Range: -1.5565

Max Act: 0.9316. Min Act: -0.0001

Data Index: 68547 (C4 (Web Text))

Max Activating Token Index: 552

Text #18

Max Range: 1.5565. Min Range: -1.5565

Max Act: 0.8775. Min Act: -0.0001

Data Index: 990240 (C4 (Web Text))

Max Activating Token Index: 228

Text #19

Max Range: 1.5565. Min Range: -1.5565

Max Act: 0.9907. Min Act: -0.0001

Data Index: 139813 (C4 (Web Text))

Max Activating Token Index: 224