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

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

Neuron 335 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8151. Min Range: -1.8151

Max Act: 1.8151. Min Act: -0.0000

Data Index: 1540251 (Python Code)

Max Activating Token Index: 31

Text #1

Max Range: 1.8151. Min Range: -1.8151

Max Act: 1.7528. Min Act: -0.0000

Data Index: 1480060 (Python Code)

Max Activating Token Index: 1013

Text #2

Max Range: 1.8151. Min Range: -1.8151

Max Act: 1.5904. Min Act: -0.0000

Data Index: 1410452 (Python Code)

Max Activating Token Index: 835

Text #3

Max Range: 1.8151. Min Range: -1.8151

Max Act: 1.4711. Min Act: -0.0000

Data Index: 392694 (C4 (Web Text))

Max Activating Token Index: 454

Text #4

Max Range: 1.8151. Min Range: -1.8151

Max Act: 1.4300. Min Act: -0.0000

Data Index: 1228600 (C4 (Web Text))

Max Activating Token Index: 116

Text #5

Max Range: 1.8151. Min Range: -1.8151

Max Act: 1.3379. Min Act: -0.0000

Data Index: 1395672 (Python Code)

Max Activating Token Index: 880

Text #6

Max Range: 1.8151. Min Range: -1.8151

Max Act: 1.4071. Min Act: -0.0000

Data Index: 235866 (C4 (Web Text))

Max Activating Token Index: 1017

Text #7

Max Range: 1.8151. Min Range: -1.8151

Max Act: 1.4799. Min Act: -0.0000

Data Index: 1507390 (Python Code)

Max Activating Token Index: 323

Text #8

Max Range: 1.8151. Min Range: -1.8151

Max Act: 1.3715. Min Act: -0.0000

Data Index: 53834 (C4 (Web Text))

Max Activating Token Index: 484

Text #9

Max Range: 1.8151. Min Range: -1.8151

Max Act: 1.2608. Min Act: -0.0000

Data Index: 359818 (C4 (Web Text))

Max Activating Token Index: 250

Text #10

Max Range: 1.8151. Min Range: -1.8151

Max Act: 1.2914. Min Act: -0.0000

Data Index: 1261081 (C4 (Web Text))

Max Activating Token Index: 418

Text #11

Max Range: 1.8151. Min Range: -1.8151

Max Act: 1.2861. Min Act: -0.0000

Data Index: 537999 (C4 (Web Text))

Max Activating Token Index: 968

Text #12

Max Range: 1.8151. Min Range: -1.8151

Max Act: 1.3797. Min Act: -0.0000

Data Index: 919497 (C4 (Web Text))

Max Activating Token Index: 350

Text #13

Max Range: 1.8151. Min Range: -1.8151

Max Act: 1.2640. Min Act: -0.0000

Data Index: 1360857 (Python Code)

Max Activating Token Index: 469

Text #14

Max Range: 1.8151. Min Range: -1.8151

Max Act: 1.1735. Min Act: -0.0000

Data Index: 3434 (C4 (Web Text))

Max Activating Token Index: 121

Text #15

Max Range: 1.8151. Min Range: -1.8151

Max Act: 1.2924. Min Act: -0.0000

Data Index: 881095 (C4 (Web Text))

Max Activating Token Index: 246

Text #16

Max Range: 1.8151. Min Range: -1.8151

Max Act: 1.2734. Min Act: -0.0000

Data Index: 705824 (C4 (Web Text))

Max Activating Token Index: 369

Text #17

Max Range: 1.8151. Min Range: -1.8151

Max Act: 1.1378. Min Act: -0.0000

Data Index: 1326025 (C4 (Web Text))

Max Activating Token Index: 551

Text #18

Max Range: 1.8151. Min Range: -1.8151

Max Act: 1.2081. Min Act: -0.0000

Data Index: 289605 (C4 (Web Text))

Max Activating Token Index: 779

Text #19

Max Range: 1.8151. Min Range: -1.8151

Max Act: 1.2023. Min Act: -0.0000

Data Index: 1557573 (Python Code)

Max Activating Token Index: 797