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

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

Neuron 4641 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.8172. Min Range: -4.8172

Max Act: 4.8172. Min Act: -0.0000

Data Index: 445162 (C4 (Web Text))

Max Activating Token Index: 792

Text #1

Max Range: 4.8172. Min Range: -4.8172

Max Act: 4.4686. Min Act: -0.0000

Data Index: 1099763 (C4 (Web Text))

Max Activating Token Index: 628

Text #2

Max Range: 4.8172. Min Range: -4.8172

Max Act: 4.1139. Min Act: -0.0000

Data Index: 1033933 (C4 (Web Text))

Max Activating Token Index: 827

Text #3

Max Range: 4.8172. Min Range: -4.8172

Max Act: 4.4424. Min Act: -0.0000

Data Index: 851139 (C4 (Web Text))

Max Activating Token Index: 411

Text #4

Max Range: 4.8172. Min Range: -4.8172

Max Act: 4.0785. Min Act: -0.0001

Data Index: 20138 (C4 (Web Text))

Max Activating Token Index: 147

Text #5

Max Range: 4.8172. Min Range: -4.8172

Max Act: 4.0985. Min Act: -0.0000

Data Index: 1355432 (C4 (Web Text))

Max Activating Token Index: 666

Text #6

Max Range: 4.8172. Min Range: -4.8172

Max Act: 4.1362. Min Act: -0.0000

Data Index: 484812 (C4 (Web Text))

Max Activating Token Index: 834

Text #7

Max Range: 4.8172. Min Range: -4.8172

Max Act: 3.6950. Min Act: -0.0000

Data Index: 906615 (C4 (Web Text))

Max Activating Token Index: 979

Text #8

Max Range: 4.8172. Min Range: -4.8172

Max Act: 3.9673. Min Act: -0.0000

Data Index: 1320831 (C4 (Web Text))

Max Activating Token Index: 757

Text #9

Max Range: 4.8172. Min Range: -4.8172

Max Act: 3.9423. Min Act: -0.0000

Data Index: 654459 (C4 (Web Text))

Max Activating Token Index: 806

Text #10

Max Range: 4.8172. Min Range: -4.8172

Max Act: 3.8346. Min Act: -0.0001

Data Index: 302190 (C4 (Web Text))

Max Activating Token Index: 876

Text #11

Max Range: 4.8172. Min Range: -4.8172

Max Act: 4.0214. Min Act: -0.0000

Data Index: 925816 (C4 (Web Text))

Max Activating Token Index: 314

Text #12

Max Range: 4.8172. Min Range: -4.8172

Max Act: 3.5220. Min Act: -0.0000

Data Index: 1305039 (C4 (Web Text))

Max Activating Token Index: 786

Text #13

Max Range: 4.8172. Min Range: -4.8172

Max Act: 3.9699. Min Act: -0.0000

Data Index: 1306969 (C4 (Web Text))

Max Activating Token Index: 737

Text #14

Max Range: 4.8172. Min Range: -4.8172

Max Act: 4.2808. Min Act: -0.0000

Data Index: 1161574 (C4 (Web Text))

Max Activating Token Index: 828

Text #15

Max Range: 4.8172. Min Range: -4.8172

Max Act: 3.9269. Min Act: -0.0001

Data Index: 253980 (C4 (Web Text))

Max Activating Token Index: 1010

Text #16

Max Range: 4.8172. Min Range: -4.8172

Max Act: 3.6764. Min Act: -0.0000

Data Index: 634747 (C4 (Web Text))

Max Activating Token Index: 781

Text #17

Max Range: 4.8172. Min Range: -4.8172

Max Act: 3.7613. Min Act: -0.0000

Data Index: 931184 (C4 (Web Text))

Max Activating Token Index: 852

Text #18

Max Range: 4.8172. Min Range: -4.8172

Max Act: 3.3789. Min Act: -0.0000

Data Index: 750165 (C4 (Web Text))

Max Activating Token Index: 784

Text #19

Max Range: 4.8172. Min Range: -4.8172

Max Act: 4.0051. Min Act: -0.0000

Data Index: 1350599 (C4 (Web Text))

Max Activating Token Index: 832