Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 725 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.6075. Min Range: -1.6075

Max Act: 1.6075. Min Act: -0.0001

Data Index: 1415615 (Python Code)

Max Activating Token Index: 458

Text #1

Max Range: 1.6075. Min Range: -1.6075

Max Act: 1.3736. Min Act: -0.0001

Data Index: 1638361 (Python Code)

Max Activating Token Index: 669

Text #2

Max Range: 1.6075. Min Range: -1.6075

Max Act: 1.5392. Min Act: -0.0001

Data Index: 1443410 (Python Code)

Max Activating Token Index: 13

Text #3

Max Range: 1.6075. Min Range: -1.6075

Max Act: 1.5392. Min Act: -0.0001

Data Index: 1471502 (Python Code)

Max Activating Token Index: 13

Text #4

Max Range: 1.6075. Min Range: -1.6075

Max Act: 1.5392. Min Act: -0.0001

Data Index: 1428993 (Python Code)

Max Activating Token Index: 13

Text #5

Max Range: 1.6075. Min Range: -1.6075

Max Act: 1.5392. Min Act: -0.0001

Data Index: 1639279 (Python Code)

Max Activating Token Index: 13

Text #6

Max Range: 1.6075. Min Range: -1.6075

Max Act: 1.4713. Min Act: -0.0000

Data Index: 1623973 (Python Code)

Max Activating Token Index: 12

Text #7

Max Range: 1.6075. Min Range: -1.6075

Max Act: 1.4713. Min Act: -0.0001

Data Index: 1644867 (Python Code)

Max Activating Token Index: 12

Text #8

Max Range: 1.6075. Min Range: -1.6075

Max Act: 1.4713. Min Act: -0.0001

Data Index: 1553857 (Python Code)

Max Activating Token Index: 12

Text #9

Max Range: 1.6075. Min Range: -1.6075

Max Act: 1.4713. Min Act: -0.0000

Data Index: 1618148 (Python Code)

Max Activating Token Index: 12

Text #10

Max Range: 1.6075. Min Range: -1.6075

Max Act: 1.4713. Min Act: -0.0001

Data Index: 1574807 (Python Code)

Max Activating Token Index: 12

Text #11

Max Range: 1.6075. Min Range: -1.6075

Max Act: 1.4713. Min Act: -0.0001

Data Index: 1539843 (Python Code)

Max Activating Token Index: 12

Text #12

Max Range: 1.6075. Min Range: -1.6075

Max Act: 1.4637. Min Act: -0.0001

Data Index: 1638388 (Python Code)

Max Activating Token Index: 338

Text #13

Max Range: 1.6075. Min Range: -1.6075

Max Act: 1.4664. Min Act: -0.0000

Data Index: 1604184 (Python Code)

Max Activating Token Index: 27

Text #14

Max Range: 1.6075. Min Range: -1.6075

Max Act: 1.4430. Min Act: -0.0001

Data Index: 1500996 (Python Code)

Max Activating Token Index: 16

Text #15

Max Range: 1.6075. Min Range: -1.6075

Max Act: 1.5236. Min Act: -0.0001

Data Index: 1360474 (Python Code)

Max Activating Token Index: 240

Text #16

Max Range: 1.6075. Min Range: -1.6075

Max Act: 1.3790. Min Act: -0.0001

Data Index: 1377954 (Python Code)

Max Activating Token Index: 487

Text #17

Max Range: 1.6075. Min Range: -1.6075

Max Act: 1.4597. Min Act: -0.0001

Data Index: 1378392 (Python Code)

Max Activating Token Index: 109

Text #18

Max Range: 1.6075. Min Range: -1.6075

Max Act: 1.3477. Min Act: -0.0001

Data Index: 1473765 (Python Code)

Max Activating Token Index: 299

Text #19

Max Range: 1.6075. Min Range: -1.6075

Max Act: 1.3175. Min Act: -0.0001

Data Index: 1530851 (Python Code)

Max Activating Token Index: 7