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

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

Neuron 1509 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9549. Min Range: -0.9549

Max Act: 0.9549. Min Act: -0.0000

Data Index: 861705 (C4 (Web Text))

Max Activating Token Index: 923

Text #1

Max Range: 0.9549. Min Range: -0.9549

Max Act: 0.8412. Min Act: -0.0000

Data Index: 1277654 (C4 (Web Text))

Max Activating Token Index: 726

Text #2

Max Range: 0.9549. Min Range: -0.9549

Max Act: 0.8250. Min Act: -0.0000

Data Index: 310683 (C4 (Web Text))

Max Activating Token Index: 1001

Text #3

Max Range: 0.9549. Min Range: -0.9549

Max Act: 0.8699. Min Act: -0.0000

Data Index: 469401 (C4 (Web Text))

Max Activating Token Index: 898

Text #4

Max Range: 0.9549. Min Range: -0.9549

Max Act: 0.8553. Min Act: -0.0000

Data Index: 1015130 (C4 (Web Text))

Max Activating Token Index: 418

Text #5

Max Range: 0.9549. Min Range: -0.9549

Max Act: 0.7675. Min Act: -0.0000

Data Index: 72629 (C4 (Web Text))

Max Activating Token Index: 964

Text #6

Max Range: 0.9549. Min Range: -0.9549

Max Act: 0.8370. Min Act: -0.0000

Data Index: 1084465 (C4 (Web Text))

Max Activating Token Index: 529

Text #7

Max Range: 0.9549. Min Range: -0.9549

Max Act: 0.7859. Min Act: -0.0000

Data Index: 753996 (C4 (Web Text))

Max Activating Token Index: 338

Text #8

Max Range: 0.9549. Min Range: -0.9549

Max Act: 0.8079. Min Act: -0.0000

Data Index: 228917 (C4 (Web Text))

Max Activating Token Index: 128

Text #9

Max Range: 0.9549. Min Range: -0.9549

Max Act: 0.7529. Min Act: -0.0000

Data Index: 608276 (C4 (Web Text))

Max Activating Token Index: 558

Text #10

Max Range: 0.9549. Min Range: -0.9549

Max Act: 0.7932. Min Act: -0.0000

Data Index: 193393 (C4 (Web Text))

Max Activating Token Index: 16

Text #11

Max Range: 0.9549. Min Range: -0.9549

Max Act: 0.7012. Min Act: -0.0001

Data Index: 555285 (C4 (Web Text))

Max Activating Token Index: 980

Text #12

Max Range: 0.9549. Min Range: -0.9549

Max Act: 0.7290. Min Act: -0.0001

Data Index: 359508 (C4 (Web Text))

Max Activating Token Index: 745

Text #13

Max Range: 0.9549. Min Range: -0.9549

Max Act: 0.7668. Min Act: -0.0000

Data Index: 582184 (C4 (Web Text))

Max Activating Token Index: 926

Text #14

Max Range: 0.9549. Min Range: -0.9549

Max Act: 0.7245. Min Act: -0.0000

Data Index: 685841 (C4 (Web Text))

Max Activating Token Index: 839

Text #15

Max Range: 0.9549. Min Range: -0.9549

Max Act: 0.7417. Min Act: -0.0000

Data Index: 653859 (C4 (Web Text))

Max Activating Token Index: 938

Text #16

Max Range: 0.9549. Min Range: -0.9549

Max Act: 0.7028. Min Act: -0.0000

Data Index: 815200 (C4 (Web Text))

Max Activating Token Index: 607

Text #17

Max Range: 0.9549. Min Range: -0.9549

Max Act: 0.6498. Min Act: -0.0000

Data Index: 699046 (C4 (Web Text))

Max Activating Token Index: 228

Text #18

Max Range: 0.9549. Min Range: -0.9549

Max Act: 0.7156. Min Act: -0.0001

Data Index: 1524970 (Python Code)

Max Activating Token Index: 12

Text #19

Max Range: 0.9549. Min Range: -0.9549

Max Act: 0.7009. Min Act: -0.0000

Data Index: 589390 (C4 (Web Text))

Max Activating Token Index: 270