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

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

Neuron 3367 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: 0.1758. Min Range: -0.1758

Max Act: 0.1758. Min Act: -0.0000

Data Index: 1301196 (C4 (Web Text))

Max Activating Token Index: 392

Text #1

Max Range: 0.1758. Min Range: -0.1758

Max Act: 0.1750. Min Act: -0.0000

Data Index: 1327841 (C4 (Web Text))

Max Activating Token Index: 412

Text #2

Max Range: 0.1758. Min Range: -0.1758

Max Act: 0.1674. Min Act: -0.0000

Data Index: 408835 (C4 (Web Text))

Max Activating Token Index: 16

Text #3

Max Range: 0.1758. Min Range: -0.1758

Max Act: 0.1717. Min Act: -0.0000

Data Index: 983222 (C4 (Web Text))

Max Activating Token Index: 604

Text #4

Max Range: 0.1758. Min Range: -0.1758

Max Act: 0.1623. Min Act: -0.0000

Data Index: 809186 (C4 (Web Text))

Max Activating Token Index: 455

Text #5

Max Range: 0.1758. Min Range: -0.1758

Max Act: 0.1610. Min Act: -0.0000

Data Index: 858697 (C4 (Web Text))

Max Activating Token Index: 960

Text #6

Max Range: 0.1758. Min Range: -0.1758

Max Act: 0.1716. Min Act: -0.0000

Data Index: 1032724 (C4 (Web Text))

Max Activating Token Index: 833

Text #7

Max Range: 0.1758. Min Range: -0.1758

Max Act: 0.1569. Min Act: -0.0000

Data Index: 203544 (C4 (Web Text))

Max Activating Token Index: 75

Text #8

Max Range: 0.1758. Min Range: -0.1758

Max Act: 0.1560. Min Act: -0.0000

Data Index: 360682 (C4 (Web Text))

Max Activating Token Index: 656

Text #9

Max Range: 0.1758. Min Range: -0.1758

Max Act: 0.1606. Min Act: -0.0000

Data Index: 528406 (C4 (Web Text))

Max Activating Token Index: 202

Text #10

Max Range: 0.1758. Min Range: -0.1758

Max Act: 0.1558. Min Act: -0.0000

Data Index: 220936 (C4 (Web Text))

Max Activating Token Index: 667

Text #11

Max Range: 0.1758. Min Range: -0.1758

Max Act: 0.1595. Min Act: -0.0000

Data Index: 252051 (C4 (Web Text))

Max Activating Token Index: 967

Text #12

Max Range: 0.1758. Min Range: -0.1758

Max Act: 0.1545. Min Act: -0.0000

Data Index: 409296 (C4 (Web Text))

Max Activating Token Index: 10

Text #13

Max Range: 0.1758. Min Range: -0.1758

Max Act: 0.1534. Min Act: -0.0000

Data Index: 728095 (C4 (Web Text))

Max Activating Token Index: 184

Text #14

Max Range: 0.1758. Min Range: -0.1758

Max Act: 0.1598. Min Act: -0.0000

Data Index: 324433 (C4 (Web Text))

Max Activating Token Index: 172

Text #15

Max Range: 0.1758. Min Range: -0.1758

Max Act: 0.1481. Min Act: -0.0000

Data Index: 639796 (C4 (Web Text))

Max Activating Token Index: 833

Text #16

Max Range: 0.1758. Min Range: -0.1758

Max Act: 0.1520. Min Act: -0.0000

Data Index: 1068893 (C4 (Web Text))

Max Activating Token Index: 103

Text #17

Max Range: 0.1758. Min Range: -0.1758

Max Act: 0.1465. Min Act: -0.0000

Data Index: 703933 (C4 (Web Text))

Max Activating Token Index: 294

Text #18

Max Range: 0.1758. Min Range: -0.1758

Max Act: 0.1457. Min Act: -0.0000

Data Index: 315933 (C4 (Web Text))

Max Activating Token Index: 57

Text #19

Max Range: 0.1758. Min Range: -0.1758

Max Act: 0.1503. Min Act: -0.0000

Data Index: 1221307 (C4 (Web Text))

Max Activating Token Index: 625