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

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

Neuron 3658 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7396. Min Range: -0.7396

Max Act: 0.6701. Min Act: -0.0000

Data Index: 1590951 (Python Code)

Max Activating Token Index: 963

Text #1

Max Range: 0.7396. Min Range: -0.7396

Max Act: 0.7162. Min Act: -0.0000

Data Index: 1418320 (Python Code)

Max Activating Token Index: 928

Text #2

Max Range: 0.7396. Min Range: -0.7396

Max Act: 0.6979. Min Act: -0.0000

Data Index: 1585713 (Python Code)

Max Activating Token Index: 997

Text #3

Max Range: 0.7396. Min Range: -0.7396

Max Act: 0.5747. Min Act: -0.0000

Data Index: 1650734 (Python Code)

Max Activating Token Index: 968

Text #4

Max Range: 0.7396. Min Range: -0.7396

Max Act: 0.6156. Min Act: -0.0000

Data Index: 652667 (C4 (Web Text))

Max Activating Token Index: 859

Text #5

Max Range: 0.7396. Min Range: -0.7396

Max Act: 0.5824. Min Act: -0.0000

Data Index: 664283 (C4 (Web Text))

Max Activating Token Index: 307

Text #6

Max Range: 0.7396. Min Range: -0.7396

Max Act: 0.5464. Min Act: -0.0000

Data Index: 227482 (C4 (Web Text))

Max Activating Token Index: 409

Text #7

Max Range: 0.7396. Min Range: -0.7396

Max Act: 0.6354. Min Act: -0.0000

Data Index: 558170 (C4 (Web Text))

Max Activating Token Index: 151

Text #8

Max Range: 0.7396. Min Range: -0.7396

Max Act: 0.6645. Min Act: -0.0000

Data Index: 1654707 (Python Code)

Max Activating Token Index: 702

Text #9

Max Range: 0.7396. Min Range: -0.7396

Max Act: 0.6283. Min Act: -0.0000

Data Index: 513061 (C4 (Web Text))

Max Activating Token Index: 688

Text #10

Max Range: 0.7396. Min Range: -0.7396

Max Act: 0.6842. Min Act: -0.0000

Data Index: 1495777 (Python Code)

Max Activating Token Index: 615

Text #11

Max Range: 0.7396. Min Range: -0.7396

Max Act: 0.5728. Min Act: -0.0000

Data Index: 667708 (C4 (Web Text))

Max Activating Token Index: 960

Text #12

Max Range: 0.7396. Min Range: -0.7396

Max Act: 0.5596. Min Act: -0.0000

Data Index: 1461028 (Python Code)

Max Activating Token Index: 916

Text #13

Max Range: 0.7396. Min Range: -0.7396

Max Act: 0.6387. Min Act: -0.0000

Data Index: 258611 (C4 (Web Text))

Max Activating Token Index: 769

Text #14

Max Range: 0.7396. Min Range: -0.7396

Max Act: 0.7396. Min Act: -0.0000

Data Index: 1378658 (Python Code)

Max Activating Token Index: 589

Text #15

Max Range: 0.7396. Min Range: -0.7396

Max Act: 0.5634. Min Act: -0.0000

Data Index: 861053 (C4 (Web Text))

Max Activating Token Index: 961

Text #16

Max Range: 0.7396. Min Range: -0.7396

Max Act: 0.6468. Min Act: -0.0000

Data Index: 603097 (C4 (Web Text))

Max Activating Token Index: 452

Text #17

Max Range: 0.7396. Min Range: -0.7396

Max Act: 0.5466. Min Act: -0.0000

Data Index: 649122 (C4 (Web Text))

Max Activating Token Index: 36

Text #18

Max Range: 0.7396. Min Range: -0.7396

Max Act: 0.5089. Min Act: -0.0000

Data Index: 1245568 (C4 (Web Text))

Max Activating Token Index: 277

Text #19

Max Range: 0.7396. Min Range: -0.7396

Max Act: 0.5583. Min Act: -0.0000

Data Index: 396513 (C4 (Web Text))

Max Activating Token Index: 657