Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3337 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.8507. Min Range: -0.8507

Max Act: 0.8507. Min Act: -0.0001

Data Index: 178925 (C4 (Web Text))

Max Activating Token Index: 24

Text #1

Max Range: 0.8507. Min Range: -0.8507

Max Act: 0.8405. Min Act: -0.0001

Data Index: 1259657 (C4 (Web Text))

Max Activating Token Index: 852

Text #2

Max Range: 0.8507. Min Range: -0.8507

Max Act: 0.7047. Min Act: -0.0001

Data Index: 823170 (C4 (Web Text))

Max Activating Token Index: 386

Text #3

Max Range: 0.8507. Min Range: -0.8507

Max Act: 0.7567. Min Act: -0.0001

Data Index: 1157742 (C4 (Web Text))

Max Activating Token Index: 73

Text #4

Max Range: 0.8507. Min Range: -0.8507

Max Act: 0.7031. Min Act: -0.0001

Data Index: 1342524 (C4 (Web Text))

Max Activating Token Index: 303

Text #5

Max Range: 0.8507. Min Range: -0.8507

Max Act: 0.7196. Min Act: -0.0001

Data Index: 112897 (C4 (Web Text))

Max Activating Token Index: 28

Text #6

Max Range: 0.8507. Min Range: -0.8507

Max Act: 0.7484. Min Act: -0.0001

Data Index: 65501 (C4 (Web Text))

Max Activating Token Index: 399

Text #7

Max Range: 0.8507. Min Range: -0.8507

Max Act: 0.7236. Min Act: -0.0001

Data Index: 147983 (C4 (Web Text))

Max Activating Token Index: 565

Text #8

Max Range: 0.8507. Min Range: -0.8507

Max Act: 0.7490. Min Act: -0.0001

Data Index: 1167912 (C4 (Web Text))

Max Activating Token Index: 695

Text #9

Max Range: 0.8507. Min Range: -0.8507

Max Act: 0.6954. Min Act: -0.0001

Data Index: 49178 (C4 (Web Text))

Max Activating Token Index: 472

Text #10

Max Range: 0.8507. Min Range: -0.8507

Max Act: 0.6696. Min Act: -0.0001

Data Index: 213102 (C4 (Web Text))

Max Activating Token Index: 416

Text #11

Max Range: 0.8507. Min Range: -0.8507

Max Act: 0.6479. Min Act: -0.0001

Data Index: 115621 (C4 (Web Text))

Max Activating Token Index: 577

Text #12

Max Range: 0.8507. Min Range: -0.8507

Max Act: 0.6845. Min Act: -0.0001

Data Index: 784325 (C4 (Web Text))

Max Activating Token Index: 534

Text #13

Max Range: 0.8507. Min Range: -0.8507

Max Act: 0.6240. Min Act: -0.0001

Data Index: 947926 (C4 (Web Text))

Max Activating Token Index: 915

Text #14

Max Range: 0.8507. Min Range: -0.8507

Max Act: 0.6576. Min Act: -0.0001

Data Index: 411300 (C4 (Web Text))

Max Activating Token Index: 72

Text #15

Max Range: 0.8507. Min Range: -0.8507

Max Act: 0.5610. Min Act: -0.0001

Data Index: 143244 (C4 (Web Text))

Max Activating Token Index: 207

Text #16

Max Range: 0.8507. Min Range: -0.8507

Max Act: 0.6475. Min Act: -0.0001

Data Index: 1286631 (C4 (Web Text))

Max Activating Token Index: 482

Text #17

Max Range: 0.8507. Min Range: -0.8507

Max Act: 0.6357. Min Act: -0.0001

Data Index: 980993 (C4 (Web Text))

Max Activating Token Index: 887

Text #18

Max Range: 0.8507. Min Range: -0.8507

Max Act: 0.6569. Min Act: -0.0001

Data Index: 1313481 (C4 (Web Text))

Max Activating Token Index: 896

Text #19

Max Range: 0.8507. Min Range: -0.8507

Max Act: 0.6700. Min Act: -0.0001

Data Index: 299504 (C4 (Web Text))

Max Activating Token Index: 289