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

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

Neuron 1266 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4749. Min Range: -1.4749

Max Act: 1.4069. Min Act: -0.0000

Data Index: 1572514 (Python Code)

Max Activating Token Index: 680

Text #1

Max Range: 1.4749. Min Range: -1.4749

Max Act: 1.4749. Min Act: -0.0000

Data Index: 1451760 (Python Code)

Max Activating Token Index: 774

Text #2

Max Range: 1.4749. Min Range: -1.4749

Max Act: 1.2299. Min Act: -0.0000

Data Index: 1493775 (Python Code)

Max Activating Token Index: 297

Text #3

Max Range: 1.4749. Min Range: -1.4749

Max Act: 1.3175. Min Act: -0.0000

Data Index: 1484778 (Python Code)

Max Activating Token Index: 193

Text #4

Max Range: 1.4749. Min Range: -1.4749

Max Act: 1.3839. Min Act: 0.0000

Data Index: 1373112 (Python Code)

Max Activating Token Index: 817

Text #5

Max Range: 1.4749. Min Range: -1.4749

Max Act: 1.3046. Min Act: 0.0001

Data Index: 1362780 (Python Code)

Max Activating Token Index: 57

Text #6

Max Range: 1.4749. Min Range: -1.4749

Max Act: 1.2546. Min Act: -0.0000

Data Index: 1638618 (Python Code)

Max Activating Token Index: 459

Text #7

Max Range: 1.4749. Min Range: -1.4749

Max Act: 1.2063. Min Act: -0.0000

Data Index: 1501275 (Python Code)

Max Activating Token Index: 419

Text #8

Max Range: 1.4749. Min Range: -1.4749

Max Act: 1.1370. Min Act: 0.0000

Data Index: 1600700 (Python Code)

Max Activating Token Index: 268

Text #9

Max Range: 1.4749. Min Range: -1.4749

Max Act: 1.1898. Min Act: -0.0000

Data Index: 1631378 (Python Code)

Max Activating Token Index: 540

Text #10

Max Range: 1.4749. Min Range: -1.4749

Max Act: 1.1911. Min Act: 0.0001

Data Index: 1575149 (Python Code)

Max Activating Token Index: 513

Text #11

Max Range: 1.4749. Min Range: -1.4749

Max Act: 1.1770. Min Act: -0.0000

Data Index: 1476690 (Python Code)

Max Activating Token Index: 909

Text #12

Max Range: 1.4749. Min Range: -1.4749

Max Act: 1.0829. Min Act: -0.0000

Data Index: 875899 (C4 (Web Text))

Max Activating Token Index: 760

Text #13

Max Range: 1.4749. Min Range: -1.4749

Max Act: 1.2452. Min Act: -0.0000

Data Index: 591576 (C4 (Web Text))

Max Activating Token Index: 849

Text #14

Max Range: 1.4749. Min Range: -1.4749

Max Act: 1.1495. Min Act: -0.0000

Data Index: 1496762 (Python Code)

Max Activating Token Index: 265

Text #15

Max Range: 1.4749. Min Range: -1.4749

Max Act: 1.2514. Min Act: 0.0000

Data Index: 1541905 (Python Code)

Max Activating Token Index: 237

Text #16

Max Range: 1.4749. Min Range: -1.4749

Max Act: 1.2018. Min Act: 0.0000

Data Index: 1465305 (Python Code)

Max Activating Token Index: 188

Text #17

Max Range: 1.4749. Min Range: -1.4749

Max Act: 1.0860. Min Act: -0.0000

Data Index: 1499200 (Python Code)

Max Activating Token Index: 667

Text #18

Max Range: 1.4749. Min Range: -1.4749

Max Act: 1.1786. Min Act: 0.0000

Data Index: 1529687 (Python Code)

Max Activating Token Index: 152

Text #19

Max Range: 1.4749. Min Range: -1.4749

Max Act: 1.0450. Min Act: -0.0000

Data Index: 844746 (C4 (Web Text))

Max Activating Token Index: 201