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

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

Neuron 1431 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6154. Min Range: -0.6154

Max Act: 0.6154. Min Act: -0.0000

Data Index: 1460248 (Python Code)

Max Activating Token Index: 657

Text #1

Max Range: 0.6154. Min Range: -0.6154

Max Act: 0.5698. Min Act: -0.0000

Data Index: 1553101 (Python Code)

Max Activating Token Index: 845

Text #2

Max Range: 0.6154. Min Range: -0.6154

Max Act: 0.5728. Min Act: -0.0000

Data Index: 1410046 (Python Code)

Max Activating Token Index: 835

Text #3

Max Range: 0.6154. Min Range: -0.6154

Max Act: 0.5198. Min Act: -0.0000

Data Index: 1361114 (Python Code)

Max Activating Token Index: 374

Text #4

Max Range: 0.6154. Min Range: -0.6154

Max Act: 0.4937. Min Act: -0.0000

Data Index: 1629790 (Python Code)

Max Activating Token Index: 621

Text #5

Max Range: 0.6154. Min Range: -0.6154

Max Act: 0.5372. Min Act: -0.0000

Data Index: 305171 (C4 (Web Text))

Max Activating Token Index: 31

Text #6

Max Range: 0.6154. Min Range: -0.6154

Max Act: 0.4989. Min Act: -0.0000

Data Index: 1372679 (Python Code)

Max Activating Token Index: 652

Text #7

Max Range: 0.6154. Min Range: -0.6154

Max Act: 0.4612. Min Act: -0.0000

Data Index: 1549890 (Python Code)

Max Activating Token Index: 628

Text #8

Max Range: 0.6154. Min Range: -0.6154

Max Act: 0.4836. Min Act: -0.0000

Data Index: 940090 (C4 (Web Text))

Max Activating Token Index: 115

Text #9

Max Range: 0.6154. Min Range: -0.6154

Max Act: 0.4553. Min Act: -0.0000

Data Index: 1582054 (Python Code)

Max Activating Token Index: 931

Text #10

Max Range: 0.6154. Min Range: -0.6154

Max Act: 0.4231. Min Act: -0.0000

Data Index: 1381556 (Python Code)

Max Activating Token Index: 770

Text #11

Max Range: 0.6154. Min Range: -0.6154

Max Act: 0.4363. Min Act: -0.0000

Data Index: 1643230 (Python Code)

Max Activating Token Index: 636

Text #12

Max Range: 0.6154. Min Range: -0.6154

Max Act: 0.4533. Min Act: -0.0000

Data Index: 1483370 (Python Code)

Max Activating Token Index: 790

Text #13

Max Range: 0.6154. Min Range: -0.6154

Max Act: 0.4511. Min Act: -0.0000

Data Index: 643211 (C4 (Web Text))

Max Activating Token Index: 392

Text #14

Max Range: 0.6154. Min Range: -0.6154

Max Act: 0.4553. Min Act: -0.0000

Data Index: 1652785 (Python Code)

Max Activating Token Index: 903

Text #15

Max Range: 0.6154. Min Range: -0.6154

Max Act: 0.4519. Min Act: -0.0000

Data Index: 1426551 (Python Code)

Max Activating Token Index: 443

Text #16

Max Range: 0.6154. Min Range: -0.6154

Max Act: 0.4455. Min Act: -0.0000

Data Index: 800608 (C4 (Web Text))

Max Activating Token Index: 351

Text #17

Max Range: 0.6154. Min Range: -0.6154

Max Act: 0.4259. Min Act: -0.0000

Data Index: 1555494 (Python Code)

Max Activating Token Index: 658

Text #18

Max Range: 0.6154. Min Range: -0.6154

Max Act: 0.4413. Min Act: -0.0000

Data Index: 1598728 (Python Code)

Max Activating Token Index: 836

Text #19

Max Range: 0.6154. Min Range: -0.6154

Max Act: 0.4538. Min Act: -0.0000

Data Index: 1406516 (Python Code)

Max Activating Token Index: 613