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

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

Neuron 5767 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: 3.4273. Min Range: -3.4273

Max Act: 3.4273. Min Act: -0.0000

Data Index: 1389562 (Python Code)

Max Activating Token Index: 495

Text #1

Max Range: 3.4273. Min Range: -3.4273

Max Act: 3.0945. Min Act: -0.0000

Data Index: 1511999 (Python Code)

Max Activating Token Index: 139

Text #2

Max Range: 3.4273. Min Range: -3.4273

Max Act: 2.8672. Min Act: -0.0000

Data Index: 1415495 (Python Code)

Max Activating Token Index: 544

Text #3

Max Range: 3.4273. Min Range: -3.4273

Max Act: 2.8056. Min Act: -0.0000

Data Index: 1517604 (Python Code)

Max Activating Token Index: 986

Text #4

Max Range: 3.4273. Min Range: -3.4273

Max Act: 2.8342. Min Act: -0.0000

Data Index: 1598803 (Python Code)

Max Activating Token Index: 729

Text #5

Max Range: 3.4273. Min Range: -3.4273

Max Act: 2.7765. Min Act: -0.0000

Data Index: 1503124 (Python Code)

Max Activating Token Index: 852

Text #6

Max Range: 3.4273. Min Range: -3.4273

Max Act: 2.9228. Min Act: -0.0000

Data Index: 1436227 (Python Code)

Max Activating Token Index: 626

Text #7

Max Range: 3.4273. Min Range: -3.4273

Max Act: 2.6236. Min Act: -0.0000

Data Index: 1613132 (Python Code)

Max Activating Token Index: 482

Text #8

Max Range: 3.4273. Min Range: -3.4273

Max Act: 2.8017. Min Act: -0.0000

Data Index: 1634119 (Python Code)

Max Activating Token Index: 580

Text #9

Max Range: 3.4273. Min Range: -3.4273

Max Act: 2.4013. Min Act: -0.0000

Data Index: 121153 (C4 (Web Text))

Max Activating Token Index: 818

Text #10

Max Range: 3.4273. Min Range: -3.4273

Max Act: 2.5088. Min Act: -0.0000

Data Index: 410626 (C4 (Web Text))

Max Activating Token Index: 88

Text #11

Max Range: 3.4273. Min Range: -3.4273

Max Act: 2.3352. Min Act: -0.0000

Data Index: 1606475 (Python Code)

Max Activating Token Index: 771

Text #12

Max Range: 3.4273. Min Range: -3.4273

Max Act: 2.5693. Min Act: -0.0000

Data Index: 1437081 (Python Code)

Max Activating Token Index: 322

Text #13

Max Range: 3.4273. Min Range: -3.4273

Max Act: 2.4210. Min Act: -0.0000

Data Index: 233822 (C4 (Web Text))

Max Activating Token Index: 339

Text #14

Max Range: 3.4273. Min Range: -3.4273

Max Act: 2.5441. Min Act: -0.0000

Data Index: 1340293 (C4 (Web Text))

Max Activating Token Index: 45

Text #15

Max Range: 3.4273. Min Range: -3.4273

Max Act: 2.2160. Min Act: -0.0000

Data Index: 1441539 (Python Code)

Max Activating Token Index: 399

Text #16

Max Range: 3.4273. Min Range: -3.4273

Max Act: 2.3915. Min Act: -0.0000

Data Index: 1543678 (Python Code)

Max Activating Token Index: 827

Text #17

Max Range: 3.4273. Min Range: -3.4273

Max Act: 2.4891. Min Act: -0.0000

Data Index: 1407608 (Python Code)

Max Activating Token Index: 372

Text #18

Max Range: 3.4273. Min Range: -3.4273

Max Act: 2.3671. Min Act: -0.0000

Data Index: 1543803 (Python Code)

Max Activating Token Index: 978

Text #19

Max Range: 3.4273. Min Range: -3.4273

Max Act: 2.1959. Min Act: -0.0000

Data Index: 1651266 (Python Code)

Max Activating Token Index: 768