Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1388 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.0884. Min Range: -1.0884

Max Act: 1.0884. Min Act: -0.0000

Data Index: 1623631 (Python Code)

Max Activating Token Index: 467

Text #1

Max Range: 1.0884. Min Range: -1.0884

Max Act: 1.0008. Min Act: -0.0000

Data Index: 1544276 (Python Code)

Max Activating Token Index: 515

Text #2

Max Range: 1.0884. Min Range: -1.0884

Max Act: 0.9622. Min Act: -0.0000

Data Index: 1570946 (Python Code)

Max Activating Token Index: 608

Text #3

Max Range: 1.0884. Min Range: -1.0884

Max Act: 0.8499. Min Act: -0.0001

Data Index: 1633161 (Python Code)

Max Activating Token Index: 728

Text #4

Max Range: 1.0884. Min Range: -1.0884

Max Act: 0.8944. Min Act: -0.0001

Data Index: 1635637 (Python Code)

Max Activating Token Index: 845

Text #5

Max Range: 1.0884. Min Range: -1.0884

Max Act: 0.8637. Min Act: -0.0001

Data Index: 1412152 (Python Code)

Max Activating Token Index: 1000

Text #6

Max Range: 1.0884. Min Range: -1.0884

Max Act: 0.8648. Min Act: -0.0001

Data Index: 1619969 (Python Code)

Max Activating Token Index: 622

Text #7

Max Range: 1.0884. Min Range: -1.0884

Max Act: 0.8545. Min Act: -0.0001

Data Index: 1629998 (Python Code)

Max Activating Token Index: 358

Text #8

Max Range: 1.0884. Min Range: -1.0884

Max Act: 0.8504. Min Act: -0.0000

Data Index: 1459502 (Python Code)

Max Activating Token Index: 173

Text #9

Max Range: 1.0884. Min Range: -1.0884

Max Act: 0.8019. Min Act: -0.0001

Data Index: 1565949 (Python Code)

Max Activating Token Index: 367

Text #10

Max Range: 1.0884. Min Range: -1.0884

Max Act: 0.8060. Min Act: -0.0000

Data Index: 1498827 (Python Code)

Max Activating Token Index: 628

Text #11

Max Range: 1.0884. Min Range: -1.0884

Max Act: 0.8450. Min Act: -0.0001

Data Index: 1634313 (Python Code)

Max Activating Token Index: 584

Text #12

Max Range: 1.0884. Min Range: -1.0884

Max Act: 0.7956. Min Act: -0.0000

Data Index: 1459238 (Python Code)

Max Activating Token Index: 401

Text #13

Max Range: 1.0884. Min Range: -1.0884

Max Act: 0.8747. Min Act: -0.0001

Data Index: 1517017 (Python Code)

Max Activating Token Index: 244

Text #14

Max Range: 1.0884. Min Range: -1.0884

Max Act: 0.8063. Min Act: -0.0001

Data Index: 1391484 (Python Code)

Max Activating Token Index: 651

Text #15

Max Range: 1.0884. Min Range: -1.0884

Max Act: 0.8097. Min Act: -0.0001

Data Index: 1602359 (Python Code)

Max Activating Token Index: 334

Text #16

Max Range: 1.0884. Min Range: -1.0884

Max Act: 0.8696. Min Act: -0.0001

Data Index: 1468013 (Python Code)

Max Activating Token Index: 511

Text #17

Max Range: 1.0884. Min Range: -1.0884

Max Act: 0.7706. Min Act: -0.0001

Data Index: 1502868 (Python Code)

Max Activating Token Index: 282

Text #18

Max Range: 1.0884. Min Range: -1.0884

Max Act: 0.8343. Min Act: -0.0001

Data Index: 1496575 (Python Code)

Max Activating Token Index: 547

Text #19

Max Range: 1.0884. Min Range: -1.0884

Max Act: 0.8240. Min Act: -0.0001

Data Index: 1458657 (Python Code)

Max Activating Token Index: 470