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

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

Neuron 3799 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.6429. Min Range: -0.6429

Max Act: 0.6429. Min Act: -0.0001

Data Index: 1408094 (Python Code)

Max Activating Token Index: 1023

Text #1

Max Range: 0.6429. Min Range: -0.6429

Max Act: 0.6243. Min Act: -0.0000

Data Index: 1596473 (Python Code)

Max Activating Token Index: 622

Text #2

Max Range: 0.6429. Min Range: -0.6429

Max Act: 0.5884. Min Act: -0.0001

Data Index: 1484247 (Python Code)

Max Activating Token Index: 710

Text #3

Max Range: 0.6429. Min Range: -0.6429

Max Act: 0.6025. Min Act: -0.0000

Data Index: 1524439 (Python Code)

Max Activating Token Index: 1023

Text #4

Max Range: 0.6429. Min Range: -0.6429

Max Act: 0.5928. Min Act: -0.0001

Data Index: 1422739 (Python Code)

Max Activating Token Index: 721

Text #5

Max Range: 0.6429. Min Range: -0.6429

Max Act: 0.5963. Min Act: -0.0000

Data Index: 1563201 (Python Code)

Max Activating Token Index: 523

Text #6

Max Range: 0.6429. Min Range: -0.6429

Max Act: 0.5904. Min Act: -0.0000

Data Index: 1537912 (Python Code)

Max Activating Token Index: 597

Text #7

Max Range: 0.6429. Min Range: -0.6429

Max Act: 0.5689. Min Act: -0.0001

Data Index: 1508487 (Python Code)

Max Activating Token Index: 723

Text #8

Max Range: 0.6429. Min Range: -0.6429

Max Act: 0.5848. Min Act: -0.0000

Data Index: 1455655 (Python Code)

Max Activating Token Index: 1023

Text #9

Max Range: 0.6429. Min Range: -0.6429

Max Act: 0.5848. Min Act: -0.0001

Data Index: 1531154 (Python Code)

Max Activating Token Index: 193

Text #10

Max Range: 0.6429. Min Range: -0.6429

Max Act: 0.5654. Min Act: -0.0001

Data Index: 1653669 (Python Code)

Max Activating Token Index: 1023

Text #11

Max Range: 0.6429. Min Range: -0.6429

Max Act: 0.5658. Min Act: -0.0000

Data Index: 1383907 (Python Code)

Max Activating Token Index: 735

Text #12

Max Range: 0.6429. Min Range: -0.6429

Max Act: 0.5731. Min Act: -0.0001

Data Index: 1382239 (Python Code)

Max Activating Token Index: 685

Text #13

Max Range: 0.6429. Min Range: -0.6429

Max Act: 0.5702. Min Act: -0.0000

Data Index: 1477262 (Python Code)

Max Activating Token Index: 953

Text #14

Max Range: 0.6429. Min Range: -0.6429

Max Act: 0.5837. Min Act: -0.0000

Data Index: 1631486 (Python Code)

Max Activating Token Index: 502

Text #15

Max Range: 0.6429. Min Range: -0.6429

Max Act: 0.5694. Min Act: -0.0001

Data Index: 1585386 (Python Code)

Max Activating Token Index: 804

Text #16

Max Range: 0.6429. Min Range: -0.6429

Max Act: 0.5675. Min Act: -0.0001

Data Index: 1561465 (Python Code)

Max Activating Token Index: 387

Text #17

Max Range: 0.6429. Min Range: -0.6429

Max Act: 0.5721. Min Act: -0.0000

Data Index: 1620233 (Python Code)

Max Activating Token Index: 770

Text #18

Max Range: 0.6429. Min Range: -0.6429

Max Act: 0.5727. Min Act: -0.0001

Data Index: 1375121 (Python Code)

Max Activating Token Index: 731

Text #19

Max Range: 0.6429. Min Range: -0.6429

Max Act: 0.5693. Min Act: -0.0000

Data Index: 1449003 (Python Code)

Max Activating Token Index: 749