Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3849 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1980. Min Range: -0.1980

Max Act: 0.1980. Min Act: -0.0001

Data Index: 729115 (C4 (Web Text))

Max Activating Token Index: 5

Text #1

Max Range: 0.1980. Min Range: -0.1980

Max Act: 0.1840. Min Act: -0.0001

Data Index: 146195 (C4 (Web Text))

Max Activating Token Index: 64

Text #2

Max Range: 0.1980. Min Range: -0.1980

Max Act: 0.1757. Min Act: -0.0001

Data Index: 46032 (C4 (Web Text))

Max Activating Token Index: 563

Text #3

Max Range: 0.1980. Min Range: -0.1980

Max Act: 0.1507. Min Act: -0.0001

Data Index: 1003599 (C4 (Web Text))

Max Activating Token Index: 532

Text #4

Max Range: 0.1980. Min Range: -0.1980

Max Act: 0.1617. Min Act: -0.0001

Data Index: 1185890 (C4 (Web Text))

Max Activating Token Index: 33

Text #5

Max Range: 0.1980. Min Range: -0.1980

Max Act: 0.1625. Min Act: -0.0001

Data Index: 700006 (C4 (Web Text))

Max Activating Token Index: 19

Text #6

Max Range: 0.1980. Min Range: -0.1980

Max Act: 0.1636. Min Act: -0.0001

Data Index: 779 (C4 (Web Text))

Max Activating Token Index: 345

Text #7

Max Range: 0.1980. Min Range: -0.1980

Max Act: 0.1487. Min Act: -0.0001

Data Index: 842966 (C4 (Web Text))

Max Activating Token Index: 72

Text #8

Max Range: 0.1980. Min Range: -0.1980

Max Act: 0.1559. Min Act: -0.0001

Data Index: 1100784 (C4 (Web Text))

Max Activating Token Index: 658

Text #9

Max Range: 0.1980. Min Range: -0.1980

Max Act: 0.1548. Min Act: -0.0001

Data Index: 206691 (C4 (Web Text))

Max Activating Token Index: 579

Text #10

Max Range: 0.1980. Min Range: -0.1980

Max Act: 0.1756. Min Act: -0.0001

Data Index: 602304 (C4 (Web Text))

Max Activating Token Index: 262

Text #11

Max Range: 0.1980. Min Range: -0.1980

Max Act: 0.1433. Min Act: -0.0001

Data Index: 897525 (C4 (Web Text))

Max Activating Token Index: 233

Text #12

Max Range: 0.1980. Min Range: -0.1980

Max Act: 0.1484. Min Act: -0.0001

Data Index: 693141 (C4 (Web Text))

Max Activating Token Index: 395

Text #13

Max Range: 0.1980. Min Range: -0.1980

Max Act: 0.1489. Min Act: -0.0001

Data Index: 1165208 (C4 (Web Text))

Max Activating Token Index: 272

Text #14

Max Range: 0.1980. Min Range: -0.1980

Max Act: 0.1673. Min Act: -0.0001

Data Index: 670466 (C4 (Web Text))

Max Activating Token Index: 103

Text #15

Max Range: 0.1980. Min Range: -0.1980

Max Act: 0.1425. Min Act: -0.0001

Data Index: 247021 (C4 (Web Text))

Max Activating Token Index: 72

Text #16

Max Range: 0.1980. Min Range: -0.1980

Max Act: 0.1514. Min Act: -0.0001

Data Index: 811260 (C4 (Web Text))

Max Activating Token Index: 58

Text #17

Max Range: 0.1980. Min Range: -0.1980

Max Act: 0.1086. Min Act: -0.0001

Data Index: 620981 (C4 (Web Text))

Max Activating Token Index: 205

Text #18

Max Range: 0.1980. Min Range: -0.1980

Max Act: 0.1451. Min Act: -0.0001

Data Index: 247866 (C4 (Web Text))

Max Activating Token Index: 646

Text #19

Max Range: 0.1980. Min Range: -0.1980

Max Act: 0.1558. Min Act: -0.0001

Data Index: 665543 (C4 (Web Text))

Max Activating Token Index: 315