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

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

Neuron 2422 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4199. Min Range: -1.4199

Max Act: 1.4199. Min Act: -0.0001

Data Index: 224581 (C4 (Web Text))

Max Activating Token Index: 913

Text #1

Max Range: 1.4199. Min Range: -1.4199

Max Act: 1.3567. Min Act: -0.0001

Data Index: 1238670 (C4 (Web Text))

Max Activating Token Index: 827

Text #2

Max Range: 1.4199. Min Range: -1.4199

Max Act: 1.3236. Min Act: -0.0001

Data Index: 641705 (C4 (Web Text))

Max Activating Token Index: 169

Text #3

Max Range: 1.4199. Min Range: -1.4199

Max Act: 1.3566. Min Act: -0.0001

Data Index: 585565 (C4 (Web Text))

Max Activating Token Index: 131

Text #4

Max Range: 1.4199. Min Range: -1.4199

Max Act: 1.1537. Min Act: -0.0001

Data Index: 510585 (C4 (Web Text))

Max Activating Token Index: 557

Text #5

Max Range: 1.4199. Min Range: -1.4199

Max Act: 1.2224. Min Act: -0.0001

Data Index: 24932 (C4 (Web Text))

Max Activating Token Index: 24

Text #6

Max Range: 1.4199. Min Range: -1.4199

Max Act: 1.0974. Min Act: -0.0001

Data Index: 103625 (C4 (Web Text))

Max Activating Token Index: 15

Text #7

Max Range: 1.4199. Min Range: -1.4199

Max Act: 1.0874. Min Act: -0.0001

Data Index: 1351654 (C4 (Web Text))

Max Activating Token Index: 137

Text #8

Max Range: 1.4199. Min Range: -1.4199

Max Act: 1.0404. Min Act: -0.0001

Data Index: 149459 (C4 (Web Text))

Max Activating Token Index: 772

Text #9

Max Range: 1.4199. Min Range: -1.4199

Max Act: 1.0559. Min Act: -0.0001

Data Index: 5791 (C4 (Web Text))

Max Activating Token Index: 321

Text #10

Max Range: 1.4199. Min Range: -1.4199

Max Act: 1.1742. Min Act: -0.0001

Data Index: 765366 (C4 (Web Text))

Max Activating Token Index: 856

Text #11

Max Range: 1.4199. Min Range: -1.4199

Max Act: 1.1511. Min Act: -0.0001

Data Index: 1271221 (C4 (Web Text))

Max Activating Token Index: 625

Text #12

Max Range: 1.4199. Min Range: -1.4199

Max Act: 1.0829. Min Act: -0.0001

Data Index: 212440 (C4 (Web Text))

Max Activating Token Index: 23

Text #13

Max Range: 1.4199. Min Range: -1.4199

Max Act: 1.1573. Min Act: -0.0001

Data Index: 80229 (C4 (Web Text))

Max Activating Token Index: 857

Text #14

Max Range: 1.4199. Min Range: -1.4199

Max Act: 1.1910. Min Act: -0.0001

Data Index: 26517 (C4 (Web Text))

Max Activating Token Index: 344

Text #15

Max Range: 1.4199. Min Range: -1.4199

Max Act: 1.0084. Min Act: -0.0001

Data Index: 432463 (C4 (Web Text))

Max Activating Token Index: 219

Text #16

Max Range: 1.4199. Min Range: -1.4199

Max Act: 1.1067. Min Act: -0.0001

Data Index: 232961 (C4 (Web Text))

Max Activating Token Index: 103

Text #17

Max Range: 1.4199. Min Range: -1.4199

Max Act: 1.1320. Min Act: -0.0001

Data Index: 713439 (C4 (Web Text))

Max Activating Token Index: 898

Text #18

Max Range: 1.4199. Min Range: -1.4199

Max Act: 1.0514. Min Act: -0.0001

Data Index: 1272296 (C4 (Web Text))

Max Activating Token Index: 855

Text #19

Max Range: 1.4199. Min Range: -1.4199

Max Act: 1.0538. Min Act: -0.0001

Data Index: 1088945 (C4 (Web Text))

Max Activating Token Index: 551