Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 978 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.7546. Min Range: -0.7546

Max Act: 0.7546. Min Act: -0.0000

Data Index: 1105295 (C4 (Web Text))

Max Activating Token Index: 810

Text #1

Max Range: 0.7546. Min Range: -0.7546

Max Act: 0.5983. Min Act: -0.0001

Data Index: 449672 (C4 (Web Text))

Max Activating Token Index: 669

Text #2

Max Range: 0.7546. Min Range: -0.7546

Max Act: 0.5827. Min Act: -0.0000

Data Index: 1026496 (C4 (Web Text))

Max Activating Token Index: 215

Text #3

Max Range: 0.7546. Min Range: -0.7546

Max Act: 0.5808. Min Act: -0.0000

Data Index: 1044173 (C4 (Web Text))

Max Activating Token Index: 239

Text #4

Max Range: 0.7546. Min Range: -0.7546

Max Act: 0.5342. Min Act: -0.0000

Data Index: 497656 (C4 (Web Text))

Max Activating Token Index: 153

Text #5

Max Range: 0.7546. Min Range: -0.7546

Max Act: 0.5225. Min Act: -0.0000

Data Index: 156109 (C4 (Web Text))

Max Activating Token Index: 803

Text #6

Max Range: 0.7546. Min Range: -0.7546

Max Act: 0.4976. Min Act: -0.0001

Data Index: 1030130 (C4 (Web Text))

Max Activating Token Index: 880

Text #7

Max Range: 0.7546. Min Range: -0.7546

Max Act: 0.4842. Min Act: -0.0000

Data Index: 30979 (C4 (Web Text))

Max Activating Token Index: 311

Text #8

Max Range: 0.7546. Min Range: -0.7546

Max Act: 0.5000. Min Act: -0.0001

Data Index: 927151 (C4 (Web Text))

Max Activating Token Index: 139

Text #9

Max Range: 0.7546. Min Range: -0.7546

Max Act: 0.4950. Min Act: -0.0001

Data Index: 393055 (C4 (Web Text))

Max Activating Token Index: 382

Text #10

Max Range: 0.7546. Min Range: -0.7546

Max Act: 0.4853. Min Act: -0.0001

Data Index: 504949 (C4 (Web Text))

Max Activating Token Index: 932

Text #11

Max Range: 0.7546. Min Range: -0.7546

Max Act: 0.4660. Min Act: -0.0001

Data Index: 1293307 (C4 (Web Text))

Max Activating Token Index: 150

Text #12

Max Range: 0.7546. Min Range: -0.7546

Max Act: 0.4782. Min Act: -0.0000

Data Index: 932341 (C4 (Web Text))

Max Activating Token Index: 564

Text #13

Max Range: 0.7546. Min Range: -0.7546

Max Act: 0.4569. Min Act: -0.0000

Data Index: 17156 (C4 (Web Text))

Max Activating Token Index: 820

Text #14

Max Range: 0.7546. Min Range: -0.7546

Max Act: 0.4688. Min Act: -0.0000

Data Index: 923962 (C4 (Web Text))

Max Activating Token Index: 167

Text #15

Max Range: 0.7546. Min Range: -0.7546

Max Act: 0.4346. Min Act: -0.0001

Data Index: 339751 (C4 (Web Text))

Max Activating Token Index: 182

Text #16

Max Range: 0.7546. Min Range: -0.7546

Max Act: 0.4705. Min Act: -0.0000

Data Index: 977313 (C4 (Web Text))

Max Activating Token Index: 56

Text #17

Max Range: 0.7546. Min Range: -0.7546

Max Act: 0.4810. Min Act: -0.0000

Data Index: 187040 (C4 (Web Text))

Max Activating Token Index: 839

Text #18

Max Range: 0.7546. Min Range: -0.7546

Max Act: 0.4825. Min Act: -0.0000

Data Index: 71199 (C4 (Web Text))

Max Activating Token Index: 982

Text #19

Max Range: 0.7546. Min Range: -0.7546

Max Act: 0.4802. Min Act: -0.0001

Data Index: 505264 (C4 (Web Text))

Max Activating Token Index: 707