Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 797 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.6801. Min Range: -1.6801

Max Act: 1.6070. Min Act: -0.0000

Data Index: 897918 (C4 (Web Text))

Max Activating Token Index: 538

Text #1

Max Range: 1.6801. Min Range: -1.6801

Max Act: 1.6801. Min Act: -0.0001

Data Index: 1215593 (C4 (Web Text))

Max Activating Token Index: 817

Text #2

Max Range: 1.6801. Min Range: -1.6801

Max Act: 1.5929. Min Act: -0.0001

Data Index: 757639 (C4 (Web Text))

Max Activating Token Index: 273

Text #3

Max Range: 1.6801. Min Range: -1.6801

Max Act: 1.3638. Min Act: -0.0001

Data Index: 800403 (C4 (Web Text))

Max Activating Token Index: 317

Text #4

Max Range: 1.6801. Min Range: -1.6801

Max Act: 1.4063. Min Act: -0.0000

Data Index: 1017545 (C4 (Web Text))

Max Activating Token Index: 697

Text #5

Max Range: 1.6801. Min Range: -1.6801

Max Act: 1.1214. Min Act: -0.0001

Data Index: 903440 (C4 (Web Text))

Max Activating Token Index: 981

Text #6

Max Range: 1.6801. Min Range: -1.6801

Max Act: 1.0864. Min Act: -0.0001

Data Index: 1352973 (C4 (Web Text))

Max Activating Token Index: 449

Text #7

Max Range: 1.6801. Min Range: -1.6801

Max Act: 1.1339. Min Act: -0.0001

Data Index: 644937 (C4 (Web Text))

Max Activating Token Index: 123

Text #8

Max Range: 1.6801. Min Range: -1.6801

Max Act: 1.0150. Min Act: -0.0001

Data Index: 1213664 (C4 (Web Text))

Max Activating Token Index: 970

Text #9

Max Range: 1.6801. Min Range: -1.6801

Max Act: 1.0061. Min Act: -0.0001

Data Index: 238355 (C4 (Web Text))

Max Activating Token Index: 452

Text #10

Max Range: 1.6801. Min Range: -1.6801

Max Act: 0.9061. Min Act: -0.0001

Data Index: 1057738 (C4 (Web Text))

Max Activating Token Index: 635

Text #11

Max Range: 1.6801. Min Range: -1.6801

Max Act: 0.9124. Min Act: -0.0001

Data Index: 627142 (C4 (Web Text))

Max Activating Token Index: 71

Text #12

Max Range: 1.6801. Min Range: -1.6801

Max Act: 0.9156. Min Act: -0.0001

Data Index: 648643 (C4 (Web Text))

Max Activating Token Index: 574

Text #13

Max Range: 1.6801. Min Range: -1.6801

Max Act: 0.8374. Min Act: -0.0001

Data Index: 140489 (C4 (Web Text))

Max Activating Token Index: 86

Text #14

Max Range: 1.6801. Min Range: -1.6801

Max Act: 0.7881. Min Act: -0.0001

Data Index: 1253854 (C4 (Web Text))

Max Activating Token Index: 555

Text #15

Max Range: 1.6801. Min Range: -1.6801

Max Act: 0.8489. Min Act: -0.0001

Data Index: 674911 (C4 (Web Text))

Max Activating Token Index: 728

Text #16

Max Range: 1.6801. Min Range: -1.6801

Max Act: 0.7692. Min Act: -0.0001

Data Index: 1339433 (C4 (Web Text))

Max Activating Token Index: 195

Text #17

Max Range: 1.6801. Min Range: -1.6801

Max Act: 0.7630. Min Act: -0.0001

Data Index: 534598 (C4 (Web Text))

Max Activating Token Index: 156

Text #18

Max Range: 1.6801. Min Range: -1.6801

Max Act: 0.7777. Min Act: -0.0001

Data Index: 120726 (C4 (Web Text))

Max Activating Token Index: 161

Text #19

Max Range: 1.6801. Min Range: -1.6801

Max Act: 0.7148. Min Act: -0.0001

Data Index: 167287 (C4 (Web Text))

Max Activating Token Index: 541