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

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

Neuron 721 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: 0.1321. Min Range: -0.1321

Max Act: 0.1321. Min Act: -0.0001

Data Index: 287123 (C4 (Web Text))

Max Activating Token Index: 254

Text #1

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.1304. Min Act: -0.0001

Data Index: 688580 (C4 (Web Text))

Max Activating Token Index: 691

Text #2

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.1201. Min Act: -0.0001

Data Index: 701779 (C4 (Web Text))

Max Activating Token Index: 589

Text #3

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.1166. Min Act: -0.0001

Data Index: 802949 (C4 (Web Text))

Max Activating Token Index: 237

Text #4

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.1059. Min Act: -0.0001

Data Index: 596149 (C4 (Web Text))

Max Activating Token Index: 78

Text #5

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.1066. Min Act: -0.0001

Data Index: 930279 (C4 (Web Text))

Max Activating Token Index: 579

Text #6

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.1087. Min Act: -0.0001

Data Index: 1263023 (C4 (Web Text))

Max Activating Token Index: 598

Text #7

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.1094. Min Act: -0.0001

Data Index: 907576 (C4 (Web Text))

Max Activating Token Index: 319

Text #8

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.0982. Min Act: -0.0001

Data Index: 151104 (C4 (Web Text))

Max Activating Token Index: 843

Text #9

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.1027. Min Act: -0.0001

Data Index: 747647 (C4 (Web Text))

Max Activating Token Index: 179

Text #10

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.0984. Min Act: -0.0001

Data Index: 675911 (C4 (Web Text))

Max Activating Token Index: 451

Text #11

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.0975. Min Act: -0.0001

Data Index: 1257850 (C4 (Web Text))

Max Activating Token Index: 1005

Text #12

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.0930. Min Act: -0.0001

Data Index: 906433 (C4 (Web Text))

Max Activating Token Index: 639

Text #13

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.0968. Min Act: -0.0001

Data Index: 62809 (C4 (Web Text))

Max Activating Token Index: 501

Text #14

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.1013. Min Act: -0.0001

Data Index: 827921 (C4 (Web Text))

Max Activating Token Index: 676

Text #15

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.0950. Min Act: -0.0001

Data Index: 1113195 (C4 (Web Text))

Max Activating Token Index: 1017

Text #16

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.0911. Min Act: -0.0001

Data Index: 1049346 (C4 (Web Text))

Max Activating Token Index: 289

Text #17

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.0996. Min Act: -0.0001

Data Index: 603428 (C4 (Web Text))

Max Activating Token Index: 632

Text #18

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.1031. Min Act: -0.0001

Data Index: 235113 (C4 (Web Text))

Max Activating Token Index: 243

Text #19

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.0893. Min Act: -0.0001

Data Index: 811364 (C4 (Web Text))

Max Activating Token Index: 393