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

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

Neuron 1546 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1984. Min Range: -0.1984

Max Act: 0.1984. Min Act: -0.0000

Data Index: 1346161 (C4 (Web Text))

Max Activating Token Index: 261

Text #1

Max Range: 0.1984. Min Range: -0.1984

Max Act: 0.1956. Min Act: -0.0000

Data Index: 1045416 (C4 (Web Text))

Max Activating Token Index: 393

Text #2

Max Range: 0.1984. Min Range: -0.1984

Max Act: 0.1854. Min Act: -0.0000

Data Index: 25511 (C4 (Web Text))

Max Activating Token Index: 119

Text #3

Max Range: 0.1984. Min Range: -0.1984

Max Act: 0.1829. Min Act: -0.0000

Data Index: 429763 (C4 (Web Text))

Max Activating Token Index: 629

Text #4

Max Range: 0.1984. Min Range: -0.1984

Max Act: 0.1751. Min Act: -0.0000

Data Index: 727210 (C4 (Web Text))

Max Activating Token Index: 279

Text #5

Max Range: 0.1984. Min Range: -0.1984

Max Act: 0.1665. Min Act: -0.0000

Data Index: 784450 (C4 (Web Text))

Max Activating Token Index: 457

Text #6

Max Range: 0.1984. Min Range: -0.1984

Max Act: 0.1639. Min Act: -0.0000

Data Index: 726872 (C4 (Web Text))

Max Activating Token Index: 875

Text #7

Max Range: 0.1984. Min Range: -0.1984

Max Act: 0.1690. Min Act: -0.0000

Data Index: 108047 (C4 (Web Text))

Max Activating Token Index: 263

Text #8

Max Range: 0.1984. Min Range: -0.1984

Max Act: 0.1650. Min Act: -0.0000

Data Index: 1090192 (C4 (Web Text))

Max Activating Token Index: 386

Text #9

Max Range: 0.1984. Min Range: -0.1984

Max Act: 0.1569. Min Act: -0.0000

Data Index: 746627 (C4 (Web Text))

Max Activating Token Index: 168

Text #10

Max Range: 0.1984. Min Range: -0.1984

Max Act: 0.1606. Min Act: -0.0000

Data Index: 481286 (C4 (Web Text))

Max Activating Token Index: 123

Text #11

Max Range: 0.1984. Min Range: -0.1984

Max Act: 0.1576. Min Act: -0.0000

Data Index: 737943 (C4 (Web Text))

Max Activating Token Index: 887

Text #12

Max Range: 0.1984. Min Range: -0.1984

Max Act: 0.1515. Min Act: -0.0000

Data Index: 384079 (C4 (Web Text))

Max Activating Token Index: 327

Text #13

Max Range: 0.1984. Min Range: -0.1984

Max Act: 0.1507. Min Act: -0.0000

Data Index: 780602 (C4 (Web Text))

Max Activating Token Index: 356

Text #14

Max Range: 0.1984. Min Range: -0.1984

Max Act: 0.1494. Min Act: -0.0000

Data Index: 389552 (C4 (Web Text))

Max Activating Token Index: 72

Text #15

Max Range: 0.1984. Min Range: -0.1984

Max Act: 0.1536. Min Act: -0.0000

Data Index: 828821 (C4 (Web Text))

Max Activating Token Index: 859

Text #16

Max Range: 0.1984. Min Range: -0.1984

Max Act: 0.1594. Min Act: -0.0000

Data Index: 813481 (C4 (Web Text))

Max Activating Token Index: 132

Text #17

Max Range: 0.1984. Min Range: -0.1984

Max Act: 0.1525. Min Act: -0.0000

Data Index: 851477 (C4 (Web Text))

Max Activating Token Index: 683

Text #18

Max Range: 0.1984. Min Range: -0.1984

Max Act: 0.1521. Min Act: -0.0000

Data Index: 801260 (C4 (Web Text))

Max Activating Token Index: 365

Text #19

Max Range: 0.1984. Min Range: -0.1984

Max Act: 0.1512. Min Act: -0.0000

Data Index: 1024647 (C4 (Web Text))

Max Activating Token Index: 277