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

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

Neuron 1482 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4967. Min Range: -1.4967

Max Act: 1.4967. Min Act: -0.0000

Data Index: 144784 (C4 (Web Text))

Max Activating Token Index: 274

Text #1

Max Range: 1.4967. Min Range: -1.4967

Max Act: 1.3637. Min Act: -0.0000

Data Index: 542751 (C4 (Web Text))

Max Activating Token Index: 362

Text #2

Max Range: 1.4967. Min Range: -1.4967

Max Act: 1.4078. Min Act: -0.0000

Data Index: 614752 (C4 (Web Text))

Max Activating Token Index: 364

Text #3

Max Range: 1.4967. Min Range: -1.4967

Max Act: 1.3752. Min Act: -0.0000

Data Index: 837187 (C4 (Web Text))

Max Activating Token Index: 367

Text #4

Max Range: 1.4967. Min Range: -1.4967

Max Act: 1.4154. Min Act: -0.0000

Data Index: 564798 (C4 (Web Text))

Max Activating Token Index: 305

Text #5

Max Range: 1.4967. Min Range: -1.4967

Max Act: 1.2408. Min Act: -0.0000

Data Index: 943297 (C4 (Web Text))

Max Activating Token Index: 738

Text #6

Max Range: 1.4967. Min Range: -1.4967

Max Act: 1.3303. Min Act: -0.0000

Data Index: 1325784 (C4 (Web Text))

Max Activating Token Index: 395

Text #7

Max Range: 1.4967. Min Range: -1.4967

Max Act: 1.1658. Min Act: -0.0000

Data Index: 1323797 (C4 (Web Text))

Max Activating Token Index: 863

Text #8

Max Range: 1.4967. Min Range: -1.4967

Max Act: 1.1788. Min Act: -0.0000

Data Index: 120238 (C4 (Web Text))

Max Activating Token Index: 103

Text #9

Max Range: 1.4967. Min Range: -1.4967

Max Act: 1.0807. Min Act: -0.0000

Data Index: 1059040 (C4 (Web Text))

Max Activating Token Index: 607

Text #10

Max Range: 1.4967. Min Range: -1.4967

Max Act: 1.0604. Min Act: -0.0000

Data Index: 1229784 (C4 (Web Text))

Max Activating Token Index: 389

Text #11

Max Range: 1.4967. Min Range: -1.4967

Max Act: 1.0004. Min Act: -0.0000

Data Index: 1524402 (Python Code)

Max Activating Token Index: 339

Text #12

Max Range: 1.4967. Min Range: -1.4967

Max Act: 1.0273. Min Act: -0.0000

Data Index: 615037 (C4 (Web Text))

Max Activating Token Index: 355

Text #13

Max Range: 1.4967. Min Range: -1.4967

Max Act: 1.0143. Min Act: -0.0000

Data Index: 1027787 (C4 (Web Text))

Max Activating Token Index: 626

Text #14

Max Range: 1.4967. Min Range: -1.4967

Max Act: 1.0901. Min Act: -0.0000

Data Index: 1060250 (C4 (Web Text))

Max Activating Token Index: 389

Text #15

Max Range: 1.4967. Min Range: -1.4967

Max Act: 1.0466. Min Act: -0.0000

Data Index: 1086812 (C4 (Web Text))

Max Activating Token Index: 231

Text #16

Max Range: 1.4967. Min Range: -1.4967

Max Act: 1.0137. Min Act: -0.0000

Data Index: 1336800 (C4 (Web Text))

Max Activating Token Index: 623

Text #17

Max Range: 1.4967. Min Range: -1.4967

Max Act: 0.9296. Min Act: -0.0000

Data Index: 523233 (C4 (Web Text))

Max Activating Token Index: 865

Text #18

Max Range: 1.4967. Min Range: -1.4967

Max Act: 0.9793. Min Act: -0.0000

Data Index: 1142961 (C4 (Web Text))

Max Activating Token Index: 59

Text #19

Max Range: 1.4967. Min Range: -1.4967

Max Act: 0.8910. Min Act: -0.0000

Data Index: 413359 (C4 (Web Text))

Max Activating Token Index: 310