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

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

Neuron 2270 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7788. Min Range: -2.7788

Max Act: 2.7788. Min Act: -0.0000

Data Index: 1094278 (C4 (Web Text))

Max Activating Token Index: 759

Text #1

Max Range: 2.7788. Min Range: -2.7788

Max Act: 2.1402. Min Act: -0.0000

Data Index: 1643570 (Python Code)

Max Activating Token Index: 504

Text #2

Max Range: 2.7788. Min Range: -2.7788

Max Act: 1.7945. Min Act: -0.0000

Data Index: 759557 (C4 (Web Text))

Max Activating Token Index: 873

Text #3

Max Range: 2.7788. Min Range: -2.7788

Max Act: 1.6412. Min Act: -0.0000

Data Index: 1565517 (Python Code)

Max Activating Token Index: 80

Text #4

Max Range: 2.7788. Min Range: -2.7788

Max Act: 1.5515. Min Act: -0.0000

Data Index: 1402821 (Python Code)

Max Activating Token Index: 741

Text #5

Max Range: 2.7788. Min Range: -2.7788

Max Act: 1.3521. Min Act: -0.0000

Data Index: 1405040 (Python Code)

Max Activating Token Index: 540

Text #6

Max Range: 2.7788. Min Range: -2.7788

Max Act: 1.5058. Min Act: -0.0000

Data Index: 1228550 (C4 (Web Text))

Max Activating Token Index: 740

Text #7

Max Range: 2.7788. Min Range: -2.7788

Max Act: 1.2077. Min Act: -0.0000

Data Index: 1620514 (Python Code)

Max Activating Token Index: 365

Text #8

Max Range: 2.7788. Min Range: -2.7788

Max Act: 1.3253. Min Act: -0.0000

Data Index: 1490192 (Python Code)

Max Activating Token Index: 305

Text #9

Max Range: 2.7788. Min Range: -2.7788

Max Act: 1.2270. Min Act: -0.0000

Data Index: 93853 (C4 (Web Text))

Max Activating Token Index: 182

Text #10

Max Range: 2.7788. Min Range: -2.7788

Max Act: 1.2157. Min Act: -0.0000

Data Index: 1397978 (Python Code)

Max Activating Token Index: 800

Text #11

Max Range: 2.7788. Min Range: -2.7788

Max Act: 1.2781. Min Act: -0.0000

Data Index: 1334105 (C4 (Web Text))

Max Activating Token Index: 311

Text #12

Max Range: 2.7788. Min Range: -2.7788

Max Act: 1.2624. Min Act: -0.0000

Data Index: 1478972 (Python Code)

Max Activating Token Index: 978

Text #13

Max Range: 2.7788. Min Range: -2.7788

Max Act: 1.1888. Min Act: -0.0000

Data Index: 1378294 (Python Code)

Max Activating Token Index: 992

Text #14

Max Range: 2.7788. Min Range: -2.7788

Max Act: 1.1758. Min Act: -0.0000

Data Index: 1432219 (Python Code)

Max Activating Token Index: 538

Text #15

Max Range: 2.7788. Min Range: -2.7788

Max Act: 1.1718. Min Act: -0.0000

Data Index: 1576779 (Python Code)

Max Activating Token Index: 170

Text #16

Max Range: 2.7788. Min Range: -2.7788

Max Act: 1.1557. Min Act: -0.0000

Data Index: 1169754 (C4 (Web Text))

Max Activating Token Index: 901

Text #17

Max Range: 2.7788. Min Range: -2.7788

Max Act: 1.2067. Min Act: -0.0000

Data Index: 367383 (C4 (Web Text))

Max Activating Token Index: 843

Text #18

Max Range: 2.7788. Min Range: -2.7788

Max Act: 1.1130. Min Act: -0.0000

Data Index: 1360185 (Python Code)

Max Activating Token Index: 504

Text #19

Max Range: 2.7788. Min Range: -2.7788

Max Act: 1.1025. Min Act: -0.0000

Data Index: 1245054 (C4 (Web Text))

Max Activating Token Index: 559