Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4926 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 4.1803. Min Range: -4.1803

Max Act: 4.1803. Min Act: -0.0000

Data Index: 96328 (C4 (Web Text))

Max Activating Token Index: 213

Text #1

Max Range: 4.1803. Min Range: -4.1803

Max Act: 3.6195. Min Act: -0.0000

Data Index: 975206 (C4 (Web Text))

Max Activating Token Index: 289

Text #2

Max Range: 4.1803. Min Range: -4.1803

Max Act: 3.4721. Min Act: -0.0000

Data Index: 1186825 (C4 (Web Text))

Max Activating Token Index: 993

Text #3

Max Range: 4.1803. Min Range: -4.1803

Max Act: 3.5835. Min Act: -0.0000

Data Index: 459019 (C4 (Web Text))

Max Activating Token Index: 400

Text #4

Max Range: 4.1803. Min Range: -4.1803

Max Act: 3.4477. Min Act: -0.0000

Data Index: 167695 (C4 (Web Text))

Max Activating Token Index: 695

Text #5

Max Range: 4.1803. Min Range: -4.1803

Max Act: 3.4221. Min Act: -0.0000

Data Index: 1521513 (Python Code)

Max Activating Token Index: 410

Text #6

Max Range: 4.1803. Min Range: -4.1803

Max Act: 3.3939. Min Act: -0.0000

Data Index: 584756 (C4 (Web Text))

Max Activating Token Index: 22

Text #7

Max Range: 4.1803. Min Range: -4.1803

Max Act: 3.3830. Min Act: -0.0000

Data Index: 305754 (C4 (Web Text))

Max Activating Token Index: 27

Text #8

Max Range: 4.1803. Min Range: -4.1803

Max Act: 3.4196. Min Act: -0.0000

Data Index: 1342583 (C4 (Web Text))

Max Activating Token Index: 710

Text #9

Max Range: 4.1803. Min Range: -4.1803

Max Act: 3.1405. Min Act: -0.0000

Data Index: 1623891 (Python Code)

Max Activating Token Index: 744

Text #10

Max Range: 4.1803. Min Range: -4.1803

Max Act: 3.0829. Min Act: -0.0000

Data Index: 1246417 (C4 (Web Text))

Max Activating Token Index: 110

Text #11

Max Range: 4.1803. Min Range: -4.1803

Max Act: 2.9739. Min Act: -0.0000

Data Index: 1026440 (C4 (Web Text))

Max Activating Token Index: 7

Text #12

Max Range: 4.1803. Min Range: -4.1803

Max Act: 2.9612. Min Act: -0.0000

Data Index: 127129 (C4 (Web Text))

Max Activating Token Index: 592

Text #13

Max Range: 4.1803. Min Range: -4.1803

Max Act: 2.8591. Min Act: -0.0000

Data Index: 278349 (C4 (Web Text))

Max Activating Token Index: 830

Text #14

Max Range: 4.1803. Min Range: -4.1803

Max Act: 2.9941. Min Act: -0.0000

Data Index: 1025282 (C4 (Web Text))

Max Activating Token Index: 645

Text #15

Max Range: 4.1803. Min Range: -4.1803

Max Act: 2.7288. Min Act: -0.0000

Data Index: 1646271 (Python Code)

Max Activating Token Index: 756

Text #16

Max Range: 4.1803. Min Range: -4.1803

Max Act: 2.7153. Min Act: -0.0000

Data Index: 452442 (C4 (Web Text))

Max Activating Token Index: 547

Text #17

Max Range: 4.1803. Min Range: -4.1803

Max Act: 2.6458. Min Act: -0.0000

Data Index: 1169428 (C4 (Web Text))

Max Activating Token Index: 835

Text #18

Max Range: 4.1803. Min Range: -4.1803

Max Act: 2.7728. Min Act: -0.0000

Data Index: 1529659 (Python Code)

Max Activating Token Index: 634

Text #19

Max Range: 4.1803. Min Range: -4.1803

Max Act: 2.8688. Min Act: -0.0000

Data Index: 196321 (C4 (Web Text))

Max Activating Token Index: 698