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

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

Neuron 4479 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0080. Min Range: -2.0080

Max Act: 2.0080. Min Act: 0.0000

Data Index: 1497575 (Python Code)

Max Activating Token Index: 537

Text #1

Max Range: 2.0080. Min Range: -2.0080

Max Act: 1.9723. Min Act: -0.0000

Data Index: 1523294 (Python Code)

Max Activating Token Index: 435

Text #2

Max Range: 2.0080. Min Range: -2.0080

Max Act: 1.8949. Min Act: 0.0000

Data Index: 1454906 (Python Code)

Max Activating Token Index: 702

Text #3

Max Range: 2.0080. Min Range: -2.0080

Max Act: 1.8864. Min Act: 0.0000

Data Index: 1430360 (Python Code)

Max Activating Token Index: 663

Text #4

Max Range: 2.0080. Min Range: -2.0080

Max Act: 1.2648. Min Act: 0.0000

Data Index: 1386009 (Python Code)

Max Activating Token Index: 443

Text #5

Max Range: 2.0080. Min Range: -2.0080

Max Act: 1.2601. Min Act: -0.0000

Data Index: 1649290 (Python Code)

Max Activating Token Index: 431

Text #6

Max Range: 2.0080. Min Range: -2.0080

Max Act: 1.2823. Min Act: -0.0000

Data Index: 1546040 (Python Code)

Max Activating Token Index: 980

Text #7

Max Range: 2.0080. Min Range: -2.0080

Max Act: 1.2587. Min Act: 0.0002

Data Index: 1508338 (Python Code)

Max Activating Token Index: 219

Text #8

Max Range: 2.0080. Min Range: -2.0080

Max Act: 1.2590. Min Act: -0.0000

Data Index: 1141517 (C4 (Web Text))

Max Activating Token Index: 600

Text #9

Max Range: 2.0080. Min Range: -2.0080

Max Act: 1.1660. Min Act: 0.0002

Data Index: 1553683 (Python Code)

Max Activating Token Index: 245

Text #10

Max Range: 2.0080. Min Range: -2.0080

Max Act: 1.2309. Min Act: 0.0001

Data Index: 1496750 (Python Code)

Max Activating Token Index: 418

Text #11

Max Range: 2.0080. Min Range: -2.0080

Max Act: 1.1985. Min Act: 0.0000

Data Index: 1585991 (Python Code)

Max Activating Token Index: 254

Text #12

Max Range: 2.0080. Min Range: -2.0080

Max Act: 1.1675. Min Act: -0.0000

Data Index: 1525048 (Python Code)

Max Activating Token Index: 959

Text #13

Max Range: 2.0080. Min Range: -2.0080

Max Act: 1.1679. Min Act: -0.0000

Data Index: 1387796 (Python Code)

Max Activating Token Index: 711

Text #14

Max Range: 2.0080. Min Range: -2.0080

Max Act: 1.1178. Min Act: -0.0000

Data Index: 1107691 (C4 (Web Text))

Max Activating Token Index: 391

Text #15

Max Range: 2.0080. Min Range: -2.0080

Max Act: 1.1006. Min Act: 0.0000

Data Index: 1485399 (Python Code)

Max Activating Token Index: 648

Text #16

Max Range: 2.0080. Min Range: -2.0080

Max Act: 1.1038. Min Act: -0.0000

Data Index: 1645715 (Python Code)

Max Activating Token Index: 603

Text #17

Max Range: 2.0080. Min Range: -2.0080

Max Act: 1.1070. Min Act: -0.0000

Data Index: 874757 (C4 (Web Text))

Max Activating Token Index: 137

Text #18

Max Range: 2.0080. Min Range: -2.0080

Max Act: 1.1725. Min Act: -0.0000

Data Index: 1443704 (Python Code)

Max Activating Token Index: 81

Text #19

Max Range: 2.0080. Min Range: -2.0080

Max Act: 1.1554. Min Act: -0.0000

Data Index: 1467309 (Python Code)

Max Activating Token Index: 785