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

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

Neuron 3175 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.1124. Min Act: -0.0001

Data Index: 698134 (C4 (Web Text))

Max Activating Token Index: 651

Text #1

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.1203. Min Act: -0.0001

Data Index: 60066 (C4 (Web Text))

Max Activating Token Index: 909

Text #2

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.1145. Min Act: -0.0002

Data Index: 998806 (C4 (Web Text))

Max Activating Token Index: 740

Text #3

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.1158. Min Act: -0.0002

Data Index: 468837 (C4 (Web Text))

Max Activating Token Index: 385

Text #4

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.1126. Min Act: -0.0001

Data Index: 1385024 (Python Code)

Max Activating Token Index: 496

Text #5

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.0992. Min Act: -0.0001

Data Index: 653786 (C4 (Web Text))

Max Activating Token Index: 177

Text #6

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.1029. Min Act: -0.0001

Data Index: 1154499 (C4 (Web Text))

Max Activating Token Index: 517

Text #7

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.1018. Min Act: -0.0001

Data Index: 330999 (C4 (Web Text))

Max Activating Token Index: 523

Text #8

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.0901. Min Act: -0.0001

Data Index: 577107 (C4 (Web Text))

Max Activating Token Index: 707

Text #9

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.0870. Min Act: -0.0001

Data Index: 1248870 (C4 (Web Text))

Max Activating Token Index: 822

Text #10

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.0931. Min Act: -0.0002

Data Index: 502948 (C4 (Web Text))

Max Activating Token Index: 257

Text #11

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.0969. Min Act: -0.0001

Data Index: 188225 (C4 (Web Text))

Max Activating Token Index: 848

Text #12

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.0936. Min Act: -0.0001

Data Index: 174154 (C4 (Web Text))

Max Activating Token Index: 19

Text #13

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.0837. Min Act: -0.0001

Data Index: 368046 (C4 (Web Text))

Max Activating Token Index: 1013

Text #14

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.0833. Min Act: -0.0001

Data Index: 1325041 (C4 (Web Text))

Max Activating Token Index: 672

Text #15

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.0950. Min Act: -0.0001

Data Index: 924609 (C4 (Web Text))

Max Activating Token Index: 725

Text #16

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.0846. Min Act: -0.0001

Data Index: 469261 (C4 (Web Text))

Max Activating Token Index: 519

Text #17

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.0782. Min Act: -0.0001

Data Index: 115784 (C4 (Web Text))

Max Activating Token Index: 1019

Text #18

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.0857. Min Act: -0.0001

Data Index: 207984 (C4 (Web Text))

Max Activating Token Index: 357

Text #19

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.0922. Min Act: -0.0001

Data Index: 484949 (C4 (Web Text))

Max Activating Token Index: 224