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

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

Neuron 1603 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5228. Min Range: -1.5228

Max Act: 1.5228. Min Act: -0.0000

Data Index: 537202 (C4 (Web Text))

Max Activating Token Index: 346

Text #1

Max Range: 1.5228. Min Range: -1.5228

Max Act: 1.0302. Min Act: -0.0000

Data Index: 907799 (C4 (Web Text))

Max Activating Token Index: 106

Text #2

Max Range: 1.5228. Min Range: -1.5228

Max Act: 1.0017. Min Act: -0.0000

Data Index: 911834 (C4 (Web Text))

Max Activating Token Index: 1008

Text #3

Max Range: 1.5228. Min Range: -1.5228

Max Act: 0.9339. Min Act: -0.0000

Data Index: 811197 (C4 (Web Text))

Max Activating Token Index: 568

Text #4

Max Range: 1.5228. Min Range: -1.5228

Max Act: 0.8902. Min Act: -0.0000

Data Index: 34342 (C4 (Web Text))

Max Activating Token Index: 345

Text #5

Max Range: 1.5228. Min Range: -1.5228

Max Act: 0.8564. Min Act: -0.0000

Data Index: 1071516 (C4 (Web Text))

Max Activating Token Index: 428

Text #6

Max Range: 1.5228. Min Range: -1.5228

Max Act: 0.9169. Min Act: -0.0000

Data Index: 606650 (C4 (Web Text))

Max Activating Token Index: 80

Text #7

Max Range: 1.5228. Min Range: -1.5228

Max Act: 0.8462. Min Act: 0.0001

Data Index: 963241 (C4 (Web Text))

Max Activating Token Index: 120

Text #8

Max Range: 1.5228. Min Range: -1.5228

Max Act: 0.8113. Min Act: -0.0000

Data Index: 714510 (C4 (Web Text))

Max Activating Token Index: 36

Text #9

Max Range: 1.5228. Min Range: -1.5228

Max Act: 0.8474. Min Act: -0.0000

Data Index: 285935 (C4 (Web Text))

Max Activating Token Index: 218

Text #10

Max Range: 1.5228. Min Range: -1.5228

Max Act: 0.8017. Min Act: -0.0000

Data Index: 345079 (C4 (Web Text))

Max Activating Token Index: 381

Text #11

Max Range: 1.5228. Min Range: -1.5228

Max Act: 0.8177. Min Act: -0.0000

Data Index: 796924 (C4 (Web Text))

Max Activating Token Index: 64

Text #12

Max Range: 1.5228. Min Range: -1.5228

Max Act: 0.8198. Min Act: -0.0000

Data Index: 594859 (C4 (Web Text))

Max Activating Token Index: 754

Text #13

Max Range: 1.5228. Min Range: -1.5228

Max Act: 0.7850. Min Act: -0.0000

Data Index: 589564 (C4 (Web Text))

Max Activating Token Index: 799

Text #14

Max Range: 1.5228. Min Range: -1.5228

Max Act: 0.7446. Min Act: -0.0000

Data Index: 929546 (C4 (Web Text))

Max Activating Token Index: 323

Text #15

Max Range: 1.5228. Min Range: -1.5228

Max Act: 0.7371. Min Act: -0.0000

Data Index: 879763 (C4 (Web Text))

Max Activating Token Index: 967

Text #16

Max Range: 1.5228. Min Range: -1.5228

Max Act: 0.7541. Min Act: -0.0000

Data Index: 371586 (C4 (Web Text))

Max Activating Token Index: 355

Text #17

Max Range: 1.5228. Min Range: -1.5228

Max Act: 0.7746. Min Act: 0.0000

Data Index: 996036 (C4 (Web Text))

Max Activating Token Index: 32

Text #18

Max Range: 1.5228. Min Range: -1.5228

Max Act: 0.7569. Min Act: -0.0000

Data Index: 926362 (C4 (Web Text))

Max Activating Token Index: 618

Text #19

Max Range: 1.5228. Min Range: -1.5228

Max Act: 0.7691. Min Act: -0.0000

Data Index: 62465 (C4 (Web Text))

Max Activating Token Index: 930