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

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

Neuron 4659 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.2032. Min Range: -4.2032

Max Act: 4.2032. Min Act: -0.0000

Data Index: 1154396 (C4 (Web Text))

Max Activating Token Index: 149

Text #1

Max Range: 4.2032. Min Range: -4.2032

Max Act: 3.6026. Min Act: -0.0000

Data Index: 247721 (C4 (Web Text))

Max Activating Token Index: 894

Text #2

Max Range: 4.2032. Min Range: -4.2032

Max Act: 3.4025. Min Act: -0.0000

Data Index: 1269411 (C4 (Web Text))

Max Activating Token Index: 309

Text #3

Max Range: 4.2032. Min Range: -4.2032

Max Act: 2.9423. Min Act: -0.0000

Data Index: 361495 (C4 (Web Text))

Max Activating Token Index: 918

Text #4

Max Range: 4.2032. Min Range: -4.2032

Max Act: 3.2575. Min Act: -0.0000

Data Index: 932641 (C4 (Web Text))

Max Activating Token Index: 739

Text #5

Max Range: 4.2032. Min Range: -4.2032

Max Act: 2.9448. Min Act: -0.0000

Data Index: 786355 (C4 (Web Text))

Max Activating Token Index: 621

Text #6

Max Range: 4.2032. Min Range: -4.2032

Max Act: 2.8743. Min Act: -0.0000

Data Index: 870071 (C4 (Web Text))

Max Activating Token Index: 969

Text #7

Max Range: 4.2032. Min Range: -4.2032

Max Act: 2.8986. Min Act: -0.0000

Data Index: 143782 (C4 (Web Text))

Max Activating Token Index: 822

Text #8

Max Range: 4.2032. Min Range: -4.2032

Max Act: 2.8238. Min Act: -0.0000

Data Index: 759025 (C4 (Web Text))

Max Activating Token Index: 612

Text #9

Max Range: 4.2032. Min Range: -4.2032

Max Act: 2.6030. Min Act: -0.0000

Data Index: 931267 (C4 (Web Text))

Max Activating Token Index: 342

Text #10

Max Range: 4.2032. Min Range: -4.2032

Max Act: 2.5313. Min Act: -0.0000

Data Index: 189577 (C4 (Web Text))

Max Activating Token Index: 256

Text #11

Max Range: 4.2032. Min Range: -4.2032

Max Act: 2.2976. Min Act: -0.0000

Data Index: 846041 (C4 (Web Text))

Max Activating Token Index: 252

Text #12

Max Range: 4.2032. Min Range: -4.2032

Max Act: 2.3800. Min Act: -0.0000

Data Index: 27922 (C4 (Web Text))

Max Activating Token Index: 306

Text #13

Max Range: 4.2032. Min Range: -4.2032

Max Act: 2.3185. Min Act: -0.0000

Data Index: 298005 (C4 (Web Text))

Max Activating Token Index: 810

Text #14

Max Range: 4.2032. Min Range: -4.2032

Max Act: 2.1597. Min Act: -0.0000

Data Index: 348545 (C4 (Web Text))

Max Activating Token Index: 790

Text #15

Max Range: 4.2032. Min Range: -4.2032

Max Act: 2.2540. Min Act: -0.0000

Data Index: 372487 (C4 (Web Text))

Max Activating Token Index: 309

Text #16

Max Range: 4.2032. Min Range: -4.2032

Max Act: 2.2576. Min Act: -0.0000

Data Index: 1193073 (C4 (Web Text))

Max Activating Token Index: 477

Text #17

Max Range: 4.2032. Min Range: -4.2032

Max Act: 2.1856. Min Act: -0.0000

Data Index: 113289 (C4 (Web Text))

Max Activating Token Index: 648

Text #18

Max Range: 4.2032. Min Range: -4.2032

Max Act: 2.3094. Min Act: -0.0000

Data Index: 1021259 (C4 (Web Text))

Max Activating Token Index: 824

Text #19

Max Range: 4.2032. Min Range: -4.2032

Max Act: 2.0593. Min Act: -0.0000

Data Index: 244346 (C4 (Web Text))

Max Activating Token Index: 212