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

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

Neuron 2737 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5737. Min Range: -1.5737

Max Act: 1.5737. Min Act: -0.0001

Data Index: 1452743 (Python Code)

Max Activating Token Index: 648

Text #1

Max Range: 1.5737. Min Range: -1.5737

Max Act: 1.3428. Min Act: -0.0001

Data Index: 1629395 (Python Code)

Max Activating Token Index: 350

Text #2

Max Range: 1.5737. Min Range: -1.5737

Max Act: 1.4150. Min Act: -0.0001

Data Index: 1443381 (Python Code)

Max Activating Token Index: 65

Text #3

Max Range: 1.5737. Min Range: -1.5737

Max Act: 1.3092. Min Act: -0.0001

Data Index: 649146 (C4 (Web Text))

Max Activating Token Index: 654

Text #4

Max Range: 1.5737. Min Range: -1.5737

Max Act: 1.4389. Min Act: -0.0001

Data Index: 1390426 (Python Code)

Max Activating Token Index: 231

Text #5

Max Range: 1.5737. Min Range: -1.5737

Max Act: 1.3481. Min Act: -0.0001

Data Index: 73615 (C4 (Web Text))

Max Activating Token Index: 691

Text #6

Max Range: 1.5737. Min Range: -1.5737

Max Act: 1.2773. Min Act: -0.0001

Data Index: 1267589 (C4 (Web Text))

Max Activating Token Index: 767

Text #7

Max Range: 1.5737. Min Range: -1.5737

Max Act: 1.1945. Min Act: -0.0001

Data Index: 1416144 (Python Code)

Max Activating Token Index: 548

Text #8

Max Range: 1.5737. Min Range: -1.5737

Max Act: 1.1488. Min Act: -0.0001

Data Index: 1647584 (Python Code)

Max Activating Token Index: 701

Text #9

Max Range: 1.5737. Min Range: -1.5737

Max Act: 1.1924. Min Act: -0.0001

Data Index: 1596121 (Python Code)

Max Activating Token Index: 899

Text #10

Max Range: 1.5737. Min Range: -1.5737

Max Act: 1.1439. Min Act: -0.0001

Data Index: 467763 (C4 (Web Text))

Max Activating Token Index: 256

Text #11

Max Range: 1.5737. Min Range: -1.5737

Max Act: 1.1118. Min Act: -0.0001

Data Index: 1594611 (Python Code)

Max Activating Token Index: 848

Text #12

Max Range: 1.5737. Min Range: -1.5737

Max Act: 1.1449. Min Act: -0.0001

Data Index: 642009 (C4 (Web Text))

Max Activating Token Index: 889

Text #13

Max Range: 1.5737. Min Range: -1.5737

Max Act: 1.1504. Min Act: -0.0001

Data Index: 1556292 (Python Code)

Max Activating Token Index: 449

Text #14

Max Range: 1.5737. Min Range: -1.5737

Max Act: 1.0958. Min Act: -0.0001

Data Index: 1444295 (Python Code)

Max Activating Token Index: 345

Text #15

Max Range: 1.5737. Min Range: -1.5737

Max Act: 1.0835. Min Act: -0.0001

Data Index: 215014 (C4 (Web Text))

Max Activating Token Index: 440

Text #16

Max Range: 1.5737. Min Range: -1.5737

Max Act: 1.1546. Min Act: -0.0001

Data Index: 925505 (C4 (Web Text))

Max Activating Token Index: 57

Text #17

Max Range: 1.5737. Min Range: -1.5737

Max Act: 1.0899. Min Act: -0.0001

Data Index: 515306 (C4 (Web Text))

Max Activating Token Index: 543

Text #18

Max Range: 1.5737. Min Range: -1.5737

Max Act: 1.1254. Min Act: -0.0001

Data Index: 1533374 (Python Code)

Max Activating Token Index: 145

Text #19

Max Range: 1.5737. Min Range: -1.5737

Max Act: 1.0797. Min Act: -0.0001

Data Index: 1593705 (Python Code)

Max Activating Token Index: 401