Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1293 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.1086. Min Range: -0.1086

Max Act: 0.1086. Min Act: -0.0003

Data Index: 359474 (C4 (Web Text))

Max Activating Token Index: 350

Text #1

Max Range: 0.1086. Min Range: -0.1086

Max Act: 0.1074. Min Act: -0.0003

Data Index: 735140 (C4 (Web Text))

Max Activating Token Index: 958

Text #2

Max Range: 0.1086. Min Range: -0.1086

Max Act: 0.1019. Min Act: -0.0003

Data Index: 230866 (C4 (Web Text))

Max Activating Token Index: 997

Text #3

Max Range: 0.1086. Min Range: -0.1086

Max Act: 0.1017. Min Act: -0.0003

Data Index: 592129 (C4 (Web Text))

Max Activating Token Index: 609

Text #4

Max Range: 0.1086. Min Range: -0.1086

Max Act: 0.0999. Min Act: -0.0003

Data Index: 447708 (C4 (Web Text))

Max Activating Token Index: 571

Text #5

Max Range: 0.1086. Min Range: -0.1086

Max Act: 0.1009. Min Act: -0.0003

Data Index: 53671 (C4 (Web Text))

Max Activating Token Index: 543

Text #6

Max Range: 0.1086. Min Range: -0.1086

Max Act: 0.1033. Min Act: -0.0003

Data Index: 99259 (C4 (Web Text))

Max Activating Token Index: 549

Text #7

Max Range: 0.1086. Min Range: -0.1086

Max Act: 0.1004. Min Act: -0.0002

Data Index: 714691 (C4 (Web Text))

Max Activating Token Index: 484

Text #8

Max Range: 0.1086. Min Range: -0.1086

Max Act: 0.1019. Min Act: -0.0003

Data Index: 1214965 (C4 (Web Text))

Max Activating Token Index: 634

Text #9

Max Range: 0.1086. Min Range: -0.1086

Max Act: 0.0993. Min Act: -0.0003

Data Index: 724602 (C4 (Web Text))

Max Activating Token Index: 274

Text #10

Max Range: 0.1086. Min Range: -0.1086

Max Act: 0.1014. Min Act: -0.0004

Data Index: 1098257 (C4 (Web Text))

Max Activating Token Index: 818

Text #11

Max Range: 0.1086. Min Range: -0.1086

Max Act: 0.0983. Min Act: -0.0003

Data Index: 508059 (C4 (Web Text))

Max Activating Token Index: 1014

Text #12

Max Range: 0.1086. Min Range: -0.1086

Max Act: 0.1009. Min Act: -0.0003

Data Index: 661890 (C4 (Web Text))

Max Activating Token Index: 439

Text #13

Max Range: 0.1086. Min Range: -0.1086

Max Act: 0.0977. Min Act: -0.0003

Data Index: 83242 (C4 (Web Text))

Max Activating Token Index: 965

Text #14

Max Range: 0.1086. Min Range: -0.1086

Max Act: 0.0963. Min Act: -0.0003

Data Index: 693642 (C4 (Web Text))

Max Activating Token Index: 781

Text #15

Max Range: 0.1086. Min Range: -0.1086

Max Act: 0.0963. Min Act: -0.0003

Data Index: 901579 (C4 (Web Text))

Max Activating Token Index: 664

Text #16

Max Range: 0.1086. Min Range: -0.1086

Max Act: 0.0979. Min Act: -0.0003

Data Index: 1133883 (C4 (Web Text))

Max Activating Token Index: 644

Text #17

Max Range: 0.1086. Min Range: -0.1086

Max Act: 0.0931. Min Act: -0.0003

Data Index: 639541 (C4 (Web Text))

Max Activating Token Index: 581

Text #18

Max Range: 0.1086. Min Range: -0.1086

Max Act: 0.0986. Min Act: -0.0003

Data Index: 1194950 (C4 (Web Text))

Max Activating Token Index: 1006

Text #19

Max Range: 0.1086. Min Range: -0.1086

Max Act: 0.0974. Min Act: -0.0003

Data Index: 955654 (C4 (Web Text))

Max Activating Token Index: 202