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

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

Neuron 1878 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: 1.6729. Min Range: -1.6729

Max Act: 1.6729. Min Act: -0.0001

Data Index: 1294402 (C4 (Web Text))

Max Activating Token Index: 830

Text #1

Max Range: 1.6729. Min Range: -1.6729

Max Act: 1.5778. Min Act: -0.0001

Data Index: 134122 (C4 (Web Text))

Max Activating Token Index: 70

Text #2

Max Range: 1.6729. Min Range: -1.6729

Max Act: 1.5377. Min Act: -0.0001

Data Index: 1307509 (C4 (Web Text))

Max Activating Token Index: 850

Text #3

Max Range: 1.6729. Min Range: -1.6729

Max Act: 1.4868. Min Act: -0.0001

Data Index: 313280 (C4 (Web Text))

Max Activating Token Index: 3

Text #4

Max Range: 1.6729. Min Range: -1.6729

Max Act: 1.4868. Min Act: -0.0001

Data Index: 16876 (C4 (Web Text))

Max Activating Token Index: 3

Text #5

Max Range: 1.6729. Min Range: -1.6729

Max Act: 1.3604. Min Act: -0.0001

Data Index: 499077 (C4 (Web Text))

Max Activating Token Index: 864

Text #6

Max Range: 1.6729. Min Range: -1.6729

Max Act: 1.3603. Min Act: -0.0001

Data Index: 735299 (C4 (Web Text))

Max Activating Token Index: 921

Text #7

Max Range: 1.6729. Min Range: -1.6729

Max Act: 1.4443. Min Act: -0.0001

Data Index: 1041503 (C4 (Web Text))

Max Activating Token Index: 353

Text #8

Max Range: 1.6729. Min Range: -1.6729

Max Act: 1.3921. Min Act: -0.0001

Data Index: 471371 (C4 (Web Text))

Max Activating Token Index: 26

Text #9

Max Range: 1.6729. Min Range: -1.6729

Max Act: 1.3401. Min Act: -0.0001

Data Index: 157089 (C4 (Web Text))

Max Activating Token Index: 38

Text #10

Max Range: 1.6729. Min Range: -1.6729

Max Act: 1.4308. Min Act: -0.0001

Data Index: 903606 (C4 (Web Text))

Max Activating Token Index: 644

Text #11

Max Range: 1.6729. Min Range: -1.6729

Max Act: 1.4616. Min Act: -0.0001

Data Index: 862027 (C4 (Web Text))

Max Activating Token Index: 756

Text #12

Max Range: 1.6729. Min Range: -1.6729

Max Act: 1.3117. Min Act: -0.0001

Data Index: 332897 (C4 (Web Text))

Max Activating Token Index: 809

Text #13

Max Range: 1.6729. Min Range: -1.6729

Max Act: 1.3430. Min Act: -0.0001

Data Index: 1265465 (C4 (Web Text))

Max Activating Token Index: 998

Text #14

Max Range: 1.6729. Min Range: -1.6729

Max Act: 1.3774. Min Act: -0.0001

Data Index: 390494 (C4 (Web Text))

Max Activating Token Index: 4

Text #15

Max Range: 1.6729. Min Range: -1.6729

Max Act: 1.3774. Min Act: -0.0001

Data Index: 495989 (C4 (Web Text))

Max Activating Token Index: 4

Text #16

Max Range: 1.6729. Min Range: -1.6729

Max Act: 1.4240. Min Act: -0.0001

Data Index: 387873 (C4 (Web Text))

Max Activating Token Index: 707

Text #17

Max Range: 1.6729. Min Range: -1.6729

Max Act: 1.3980. Min Act: -0.0001

Data Index: 1059972 (C4 (Web Text))

Max Activating Token Index: 647

Text #18

Max Range: 1.6729. Min Range: -1.6729

Max Act: 1.3671. Min Act: -0.0001

Data Index: 504250 (C4 (Web Text))

Max Activating Token Index: 480

Text #19

Max Range: 1.6729. Min Range: -1.6729

Max Act: 1.2774. Min Act: -0.0001

Data Index: 1292044 (C4 (Web Text))

Max Activating Token Index: 184