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

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

Neuron 4397 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8750. Min Range: -0.8750

Max Act: 0.8750. Min Act: -0.0000

Data Index: 1585691 (Python Code)

Max Activating Token Index: 392

Text #1

Max Range: 0.8750. Min Range: -0.8750

Max Act: 0.8015. Min Act: -0.0000

Data Index: 1430252 (Python Code)

Max Activating Token Index: 86

Text #2

Max Range: 0.8750. Min Range: -0.8750

Max Act: 0.8297. Min Act: -0.0000

Data Index: 1521361 (Python Code)

Max Activating Token Index: 754

Text #3

Max Range: 0.8750. Min Range: -0.8750

Max Act: 0.8737. Min Act: -0.0000

Data Index: 1493596 (Python Code)

Max Activating Token Index: 913

Text #4

Max Range: 0.8750. Min Range: -0.8750

Max Act: 0.7921. Min Act: -0.0000

Data Index: 1414263 (Python Code)

Max Activating Token Index: 474

Text #5

Max Range: 0.8750. Min Range: -0.8750

Max Act: 0.7589. Min Act: -0.0000

Data Index: 1615327 (Python Code)

Max Activating Token Index: 507

Text #6

Max Range: 0.8750. Min Range: -0.8750

Max Act: 0.7045. Min Act: -0.0000

Data Index: 1426382 (Python Code)

Max Activating Token Index: 974

Text #7

Max Range: 0.8750. Min Range: -0.8750

Max Act: 0.6738. Min Act: -0.0000

Data Index: 1502351 (Python Code)

Max Activating Token Index: 683

Text #8

Max Range: 0.8750. Min Range: -0.8750

Max Act: 0.6617. Min Act: -0.0000

Data Index: 760969 (C4 (Web Text))

Max Activating Token Index: 65

Text #9

Max Range: 0.8750. Min Range: -0.8750

Max Act: 0.6223. Min Act: -0.0000

Data Index: 1074769 (C4 (Web Text))

Max Activating Token Index: 221

Text #10

Max Range: 0.8750. Min Range: -0.8750

Max Act: 0.6558. Min Act: -0.0000

Data Index: 1387147 (Python Code)

Max Activating Token Index: 550

Text #11

Max Range: 0.8750. Min Range: -0.8750

Max Act: 0.6650. Min Act: -0.0000

Data Index: 1442132 (Python Code)

Max Activating Token Index: 973

Text #12

Max Range: 0.8750. Min Range: -0.8750

Max Act: 0.6439. Min Act: -0.0000

Data Index: 1551572 (Python Code)

Max Activating Token Index: 790

Text #13

Max Range: 0.8750. Min Range: -0.8750

Max Act: 0.5993. Min Act: -0.0000

Data Index: 722853 (C4 (Web Text))

Max Activating Token Index: 112

Text #14

Max Range: 0.8750. Min Range: -0.8750

Max Act: 0.6207. Min Act: -0.0000

Data Index: 750918 (C4 (Web Text))

Max Activating Token Index: 616

Text #15

Max Range: 0.8750. Min Range: -0.8750

Max Act: 0.6256. Min Act: -0.0000

Data Index: 416920 (C4 (Web Text))

Max Activating Token Index: 903

Text #16

Max Range: 0.8750. Min Range: -0.8750

Max Act: 0.6200. Min Act: -0.0000

Data Index: 838922 (C4 (Web Text))

Max Activating Token Index: 61

Text #17

Max Range: 0.8750. Min Range: -0.8750

Max Act: 0.5758. Min Act: -0.0000

Data Index: 487346 (C4 (Web Text))

Max Activating Token Index: 460

Text #18

Max Range: 0.8750. Min Range: -0.8750

Max Act: 0.6001. Min Act: -0.0000

Data Index: 183841 (C4 (Web Text))

Max Activating Token Index: 245

Text #19

Max Range: 0.8750. Min Range: -0.8750

Max Act: 0.5567. Min Act: -0.0000

Data Index: 1513310 (Python Code)

Max Activating Token Index: 909