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

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

Neuron 2981 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: 0.6434. Min Range: -0.6434

Max Act: 0.6434. Min Act: -0.0001

Data Index: 1633055 (Python Code)

Max Activating Token Index: 1023

Text #1

Max Range: 0.6434. Min Range: -0.6434

Max Act: 0.6113. Min Act: -0.0001

Data Index: 1410477 (Python Code)

Max Activating Token Index: 1023

Text #2

Max Range: 0.6434. Min Range: -0.6434

Max Act: 0.4982. Min Act: -0.0001

Data Index: 1429803 (Python Code)

Max Activating Token Index: 1023

Text #3

Max Range: 0.6434. Min Range: -0.6434

Max Act: 0.4985. Min Act: -0.0001

Data Index: 1619471 (Python Code)

Max Activating Token Index: 3

Text #4

Max Range: 0.6434. Min Range: -0.6434

Max Act: 0.4878. Min Act: -0.0001

Data Index: 1572023 (Python Code)

Max Activating Token Index: 15

Text #5

Max Range: 0.6434. Min Range: -0.6434

Max Act: 0.4890. Min Act: -0.0001

Data Index: 1620925 (Python Code)

Max Activating Token Index: 30

Text #6

Max Range: 0.6434. Min Range: -0.6434

Max Act: 0.4702. Min Act: -0.0001

Data Index: 1608431 (Python Code)

Max Activating Token Index: 26

Text #7

Max Range: 0.6434. Min Range: -0.6434

Max Act: 0.4633. Min Act: -0.0001

Data Index: 1510259 (Python Code)

Max Activating Token Index: 191

Text #8

Max Range: 0.6434. Min Range: -0.6434

Max Act: 0.4716. Min Act: -0.0001

Data Index: 1447221 (Python Code)

Max Activating Token Index: 967

Text #9

Max Range: 0.6434. Min Range: -0.6434

Max Act: 0.4702. Min Act: -0.0001

Data Index: 1427330 (Python Code)

Max Activating Token Index: 10

Text #10

Max Range: 0.6434. Min Range: -0.6434

Max Act: 0.4661. Min Act: -0.0001

Data Index: 1417390 (Python Code)

Max Activating Token Index: 20

Text #11

Max Range: 0.6434. Min Range: -0.6434

Max Act: 0.4609. Min Act: -0.0001

Data Index: 1630779 (Python Code)

Max Activating Token Index: 36

Text #12

Max Range: 0.6434. Min Range: -0.6434

Max Act: 0.4573. Min Act: -0.0001

Data Index: 1564786 (Python Code)

Max Activating Token Index: 25

Text #13

Max Range: 0.6434. Min Range: -0.6434

Max Act: 0.4610. Min Act: -0.0001

Data Index: 1597767 (Python Code)

Max Activating Token Index: 947

Text #14

Max Range: 0.6434. Min Range: -0.6434

Max Act: 0.4597. Min Act: -0.0001

Data Index: 1558214 (Python Code)

Max Activating Token Index: 44

Text #15

Max Range: 0.6434. Min Range: -0.6434

Max Act: 0.4538. Min Act: -0.0001

Data Index: 1577386 (Python Code)

Max Activating Token Index: 291

Text #16

Max Range: 0.6434. Min Range: -0.6434

Max Act: 0.4480. Min Act: -0.0001

Data Index: 1628361 (Python Code)

Max Activating Token Index: 643

Text #17

Max Range: 0.6434. Min Range: -0.6434

Max Act: 0.4422. Min Act: -0.0002

Data Index: 1426496 (Python Code)

Max Activating Token Index: 763

Text #18

Max Range: 0.6434. Min Range: -0.6434

Max Act: 0.4553. Min Act: -0.0001

Data Index: 1380036 (Python Code)

Max Activating Token Index: 74

Text #19

Max Range: 0.6434. Min Range: -0.6434

Max Act: 0.4579. Min Act: -0.0001

Data Index: 1429739 (Python Code)

Max Activating Token Index: 95