Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1180 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.5410. Min Range: -0.5410

Max Act: 0.5410. Min Act: -0.0003

Data Index: 788476 (C4 (Web Text))

Max Activating Token Index: 957

Text #1

Max Range: 0.5410. Min Range: -0.5410

Max Act: 0.4197. Min Act: -0.0003

Data Index: 862973 (C4 (Web Text))

Max Activating Token Index: 743

Text #2

Max Range: 0.5410. Min Range: -0.5410

Max Act: 0.3094. Min Act: -0.0003

Data Index: 1323871 (C4 (Web Text))

Max Activating Token Index: 94

Text #3

Max Range: 0.5410. Min Range: -0.5410

Max Act: 0.3215. Min Act: -0.0003

Data Index: 360409 (C4 (Web Text))

Max Activating Token Index: 688

Text #4

Max Range: 0.5410. Min Range: -0.5410

Max Act: 0.2838. Min Act: -0.0003

Data Index: 1246170 (C4 (Web Text))

Max Activating Token Index: 656

Text #5

Max Range: 0.5410. Min Range: -0.5410

Max Act: 0.3223. Min Act: -0.0003

Data Index: 1333046 (C4 (Web Text))

Max Activating Token Index: 422

Text #6

Max Range: 0.5410. Min Range: -0.5410

Max Act: 0.3153. Min Act: -0.0003

Data Index: 878792 (C4 (Web Text))

Max Activating Token Index: 194

Text #7

Max Range: 0.5410. Min Range: -0.5410

Max Act: 0.3103. Min Act: -0.0003

Data Index: 565406 (C4 (Web Text))

Max Activating Token Index: 776

Text #8

Max Range: 0.5410. Min Range: -0.5410

Max Act: 0.2793. Min Act: -0.0003

Data Index: 703083 (C4 (Web Text))

Max Activating Token Index: 126

Text #9

Max Range: 0.5410. Min Range: -0.5410

Max Act: 0.2554. Min Act: -0.0003

Data Index: 76427 (C4 (Web Text))

Max Activating Token Index: 385

Text #10

Max Range: 0.5410. Min Range: -0.5410

Max Act: 0.2678. Min Act: -0.0003

Data Index: 1108520 (C4 (Web Text))

Max Activating Token Index: 213

Text #11

Max Range: 0.5410. Min Range: -0.5410

Max Act: 0.2767. Min Act: -0.0003

Data Index: 531211 (C4 (Web Text))

Max Activating Token Index: 707

Text #12

Max Range: 0.5410. Min Range: -0.5410

Max Act: 0.2698. Min Act: -0.0003

Data Index: 1026552 (C4 (Web Text))

Max Activating Token Index: 198

Text #13

Max Range: 0.5410. Min Range: -0.5410

Max Act: 0.2710. Min Act: -0.0003

Data Index: 428165 (C4 (Web Text))

Max Activating Token Index: 776

Text #14

Max Range: 0.5410. Min Range: -0.5410

Max Act: 0.2564. Min Act: -0.0003

Data Index: 1000338 (C4 (Web Text))

Max Activating Token Index: 868

Text #15

Max Range: 0.5410. Min Range: -0.5410

Max Act: 0.2660. Min Act: -0.0003

Data Index: 690123 (C4 (Web Text))

Max Activating Token Index: 731

Text #16

Max Range: 0.5410. Min Range: -0.5410

Max Act: 0.2638. Min Act: -0.0003

Data Index: 331766 (C4 (Web Text))

Max Activating Token Index: 829

Text #17

Max Range: 0.5410. Min Range: -0.5410

Max Act: 0.2380. Min Act: -0.0003

Data Index: 306570 (C4 (Web Text))

Max Activating Token Index: 559

Text #18

Max Range: 0.5410. Min Range: -0.5410

Max Act: 0.2329. Min Act: -0.0003

Data Index: 969134 (C4 (Web Text))

Max Activating Token Index: 530

Text #19

Max Range: 0.5410. Min Range: -0.5410

Max Act: 0.2338. Min Act: -0.0003

Data Index: 1240992 (C4 (Web Text))

Max Activating Token Index: 529