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

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

Neuron 3901 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0545. Min Act: -0.0002

Data Index: 1482349 (Python Code)

Max Activating Token Index: 572

Text #1

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0643. Min Act: -0.0002

Data Index: 1186552 (C4 (Web Text))

Max Activating Token Index: 253

Text #2

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0592. Min Act: -0.0002

Data Index: 771233 (C4 (Web Text))

Max Activating Token Index: 690

Text #3

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0565. Min Act: -0.0002

Data Index: 206416 (C4 (Web Text))

Max Activating Token Index: 352

Text #4

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0591. Min Act: -0.0002

Data Index: 689066 (C4 (Web Text))

Max Activating Token Index: 16

Text #5

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0606. Min Act: -0.0002

Data Index: 887554 (C4 (Web Text))

Max Activating Token Index: 452

Text #6

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0587. Min Act: -0.0002

Data Index: 455728 (C4 (Web Text))

Max Activating Token Index: 221

Text #7

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0570. Min Act: -0.0002

Data Index: 1115348 (C4 (Web Text))

Max Activating Token Index: 195

Text #8

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0561. Min Act: -0.0002

Data Index: 760855 (C4 (Web Text))

Max Activating Token Index: 322

Text #9

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0558. Min Act: -0.0002

Data Index: 385759 (C4 (Web Text))

Max Activating Token Index: 532

Text #10

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0551. Min Act: -0.0002

Data Index: 839747 (C4 (Web Text))

Max Activating Token Index: 113

Text #11

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0529. Min Act: -0.0002

Data Index: 964675 (C4 (Web Text))

Max Activating Token Index: 838

Text #12

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0525. Min Act: -0.0002

Data Index: 881932 (C4 (Web Text))

Max Activating Token Index: 668

Text #13

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0547. Min Act: -0.0002

Data Index: 818639 (C4 (Web Text))

Max Activating Token Index: 748

Text #14

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0579. Min Act: -0.0002

Data Index: 617461 (C4 (Web Text))

Max Activating Token Index: 623

Text #15

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0533. Min Act: -0.0002

Data Index: 425901 (C4 (Web Text))

Max Activating Token Index: 122

Text #16

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0538. Min Act: -0.0002

Data Index: 1319997 (C4 (Web Text))

Max Activating Token Index: 113

Text #17

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0528. Min Act: -0.0002

Data Index: 732749 (C4 (Web Text))

Max Activating Token Index: 236

Text #18

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0542. Min Act: -0.0002

Data Index: 1227131 (C4 (Web Text))

Max Activating Token Index: 180

Text #19

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0548. Min Act: -0.0002

Data Index: 704077 (C4 (Web Text))

Max Activating Token Index: 837