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

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

Neuron 4403 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.1743. Min Range: -5.1743

Max Act: 5.1743. Min Act: -0.0000

Data Index: 1473259 (Python Code)

Max Activating Token Index: 148

Text #1

Max Range: 5.1743. Min Range: -5.1743

Max Act: 4.9478. Min Act: -0.0000

Data Index: 1333585 (C4 (Web Text))

Max Activating Token Index: 63

Text #2

Max Range: 5.1743. Min Range: -5.1743

Max Act: 4.8297. Min Act: -0.0000

Data Index: 922822 (C4 (Web Text))

Max Activating Token Index: 27

Text #3

Max Range: 5.1743. Min Range: -5.1743

Max Act: 4.9708. Min Act: -0.0000

Data Index: 486929 (C4 (Web Text))

Max Activating Token Index: 51

Text #4

Max Range: 5.1743. Min Range: -5.1743

Max Act: 4.7192. Min Act: -0.0000

Data Index: 51027 (C4 (Web Text))

Max Activating Token Index: 31

Text #5

Max Range: 5.1743. Min Range: -5.1743

Max Act: 4.5074. Min Act: -0.0000

Data Index: 1579143 (Python Code)

Max Activating Token Index: 595

Text #6

Max Range: 5.1743. Min Range: -5.1743

Max Act: 4.4822. Min Act: -0.0000

Data Index: 1622916 (Python Code)

Max Activating Token Index: 16

Text #7

Max Range: 5.1743. Min Range: -5.1743

Max Act: 4.2074. Min Act: -0.0000

Data Index: 1118348 (C4 (Web Text))

Max Activating Token Index: 23

Text #8

Max Range: 5.1743. Min Range: -5.1743

Max Act: 4.3700. Min Act: -0.0000

Data Index: 1505095 (Python Code)

Max Activating Token Index: 637

Text #9

Max Range: 5.1743. Min Range: -5.1743

Max Act: 4.0168. Min Act: -0.0000

Data Index: 873114 (C4 (Web Text))

Max Activating Token Index: 25

Text #10

Max Range: 5.1743. Min Range: -5.1743

Max Act: 3.8162. Min Act: -0.0000

Data Index: 425549 (C4 (Web Text))

Max Activating Token Index: 37

Text #11

Max Range: 5.1743. Min Range: -5.1743

Max Act: 3.8184. Min Act: -0.0000

Data Index: 1593517 (Python Code)

Max Activating Token Index: 163

Text #12

Max Range: 5.1743. Min Range: -5.1743

Max Act: 3.6006. Min Act: -0.0000

Data Index: 1240699 (C4 (Web Text))

Max Activating Token Index: 696

Text #13

Max Range: 5.1743. Min Range: -5.1743

Max Act: 3.5901. Min Act: -0.0000

Data Index: 1423207 (Python Code)

Max Activating Token Index: 256

Text #14

Max Range: 5.1743. Min Range: -5.1743

Max Act: 3.4657. Min Act: -0.0000

Data Index: 1384785 (Python Code)

Max Activating Token Index: 440

Text #15

Max Range: 5.1743. Min Range: -5.1743

Max Act: 3.5813. Min Act: -0.0000

Data Index: 1602030 (Python Code)

Max Activating Token Index: 871

Text #16

Max Range: 5.1743. Min Range: -5.1743

Max Act: 3.5944. Min Act: -0.0000

Data Index: 656556 (C4 (Web Text))

Max Activating Token Index: 959

Text #17

Max Range: 5.1743. Min Range: -5.1743

Max Act: 3.7274. Min Act: -0.0000

Data Index: 356374 (C4 (Web Text))

Max Activating Token Index: 477

Text #18

Max Range: 5.1743. Min Range: -5.1743

Max Act: 3.5336. Min Act: -0.0000

Data Index: 1630949 (Python Code)

Max Activating Token Index: 76

Text #19

Max Range: 5.1743. Min Range: -5.1743

Max Act: 3.6864. Min Act: -0.0000

Data Index: 1362356 (Python Code)

Max Activating Token Index: 101