Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 733 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.0952. Min Act: -0.0005

Data Index: 589803 (C4 (Web Text))

Max Activating Token Index: 688

Text #1

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.1009. Min Act: -0.0005

Data Index: 1062043 (C4 (Web Text))

Max Activating Token Index: 463

Text #2

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.0978. Min Act: -0.0005

Data Index: 207461 (C4 (Web Text))

Max Activating Token Index: 603

Text #3

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.1042. Min Act: -0.0005

Data Index: 947594 (C4 (Web Text))

Max Activating Token Index: 27

Text #4

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.0937. Min Act: -0.0005

Data Index: 681905 (C4 (Web Text))

Max Activating Token Index: 860

Text #5

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.0997. Min Act: -0.0005

Data Index: 183370 (C4 (Web Text))

Max Activating Token Index: 154

Text #6

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.0972. Min Act: -0.0005

Data Index: 1236752 (C4 (Web Text))

Max Activating Token Index: 562

Text #7

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.0984. Min Act: -0.0005

Data Index: 861543 (C4 (Web Text))

Max Activating Token Index: 783

Text #8

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.1012. Min Act: -0.0005

Data Index: 1358442 (C4 (Web Text))

Max Activating Token Index: 90

Text #9

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.0947. Min Act: -0.0005

Data Index: 650026 (C4 (Web Text))

Max Activating Token Index: 25

Text #10

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.1029. Min Act: -0.0005

Data Index: 486920 (C4 (Web Text))

Max Activating Token Index: 546

Text #11

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.1004. Min Act: -0.0005

Data Index: 1068498 (C4 (Web Text))

Max Activating Token Index: 581

Text #12

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.1014. Min Act: -0.0005

Data Index: 1280038 (C4 (Web Text))

Max Activating Token Index: 786

Text #13

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.0993. Min Act: -0.0005

Data Index: 394377 (C4 (Web Text))

Max Activating Token Index: 767

Text #14

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.1014. Min Act: -0.0005

Data Index: 1132197 (C4 (Web Text))

Max Activating Token Index: 798

Text #15

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.1010. Min Act: -0.0005

Data Index: 988199 (C4 (Web Text))

Max Activating Token Index: 602

Text #16

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.0981. Min Act: -0.0005

Data Index: 1014144 (C4 (Web Text))

Max Activating Token Index: 755

Text #17

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.0901. Min Act: -0.0005

Data Index: 657640 (C4 (Web Text))

Max Activating Token Index: 464

Text #18

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.0923. Min Act: -0.0005

Data Index: 288981 (C4 (Web Text))

Max Activating Token Index: 140

Text #19

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.0967. Min Act: -0.0005

Data Index: 917085 (C4 (Web Text))

Max Activating Token Index: 555