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

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

Neuron 3013 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: 5.8488. Min Range: -5.8488

Max Act: 5.8488. Min Act: -0.0001

Data Index: 219789 (C4 (Web Text))

Max Activating Token Index: 15

Text #1

Max Range: 5.8488. Min Range: -5.8488

Max Act: 5.8074. Min Act: -0.0001

Data Index: 1351143 (C4 (Web Text))

Max Activating Token Index: 770

Text #2

Max Range: 5.8488. Min Range: -5.8488

Max Act: 4.9774. Min Act: -0.0001

Data Index: 1168874 (C4 (Web Text))

Max Activating Token Index: 19

Text #3

Max Range: 5.8488. Min Range: -5.8488

Max Act: 5.0657. Min Act: -0.0001

Data Index: 1200911 (C4 (Web Text))

Max Activating Token Index: 355

Text #4

Max Range: 5.8488. Min Range: -5.8488

Max Act: 4.8114. Min Act: -0.0001

Data Index: 631983 (C4 (Web Text))

Max Activating Token Index: 860

Text #5

Max Range: 5.8488. Min Range: -5.8488

Max Act: 4.8558. Min Act: -0.0001

Data Index: 1099718 (C4 (Web Text))

Max Activating Token Index: 442

Text #6

Max Range: 5.8488. Min Range: -5.8488

Max Act: 4.8637. Min Act: -0.0001

Data Index: 811365 (C4 (Web Text))

Max Activating Token Index: 660

Text #7

Max Range: 5.8488. Min Range: -5.8488

Max Act: 4.5871. Min Act: -0.0001

Data Index: 502849 (C4 (Web Text))

Max Activating Token Index: 354

Text #8

Max Range: 5.8488. Min Range: -5.8488

Max Act: 4.7048. Min Act: -0.0001

Data Index: 98132 (C4 (Web Text))

Max Activating Token Index: 588

Text #9

Max Range: 5.8488. Min Range: -5.8488

Max Act: 4.4601. Min Act: -0.0001

Data Index: 301285 (C4 (Web Text))

Max Activating Token Index: 564

Text #10

Max Range: 5.8488. Min Range: -5.8488

Max Act: 4.4655. Min Act: -0.0001

Data Index: 821553 (C4 (Web Text))

Max Activating Token Index: 245

Text #11

Max Range: 5.8488. Min Range: -5.8488

Max Act: 4.6208. Min Act: -0.0001

Data Index: 536511 (C4 (Web Text))

Max Activating Token Index: 896

Text #12

Max Range: 5.8488. Min Range: -5.8488

Max Act: 4.6069. Min Act: -0.0001

Data Index: 699719 (C4 (Web Text))

Max Activating Token Index: 60

Text #13

Max Range: 5.8488. Min Range: -5.8488

Max Act: 4.5640. Min Act: -0.0001

Data Index: 338995 (C4 (Web Text))

Max Activating Token Index: 673

Text #14

Max Range: 5.8488. Min Range: -5.8488

Max Act: 4.7290. Min Act: -0.0001

Data Index: 633715 (C4 (Web Text))

Max Activating Token Index: 696

Text #15

Max Range: 5.8488. Min Range: -5.8488

Max Act: 4.5425. Min Act: -0.0001

Data Index: 998544 (C4 (Web Text))

Max Activating Token Index: 819

Text #16

Max Range: 5.8488. Min Range: -5.8488

Max Act: 4.6646. Min Act: -0.0001

Data Index: 647450 (C4 (Web Text))

Max Activating Token Index: 989

Text #17

Max Range: 5.8488. Min Range: -5.8488

Max Act: 4.5128. Min Act: -0.0001

Data Index: 1271750 (C4 (Web Text))

Max Activating Token Index: 483

Text #18

Max Range: 5.8488. Min Range: -5.8488

Max Act: 4.3374. Min Act: -0.0001

Data Index: 498854 (C4 (Web Text))

Max Activating Token Index: 776

Text #19

Max Range: 5.8488. Min Range: -5.8488

Max Act: 4.1534. Min Act: -0.0001

Data Index: 531289 (C4 (Web Text))

Max Activating Token Index: 1004