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

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

Neuron 428 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2491. Min Range: -0.2491

Max Act: 0.2491. Min Act: -0.0001

Data Index: 607886 (C4 (Web Text))

Max Activating Token Index: 545

Text #1

Max Range: 0.2491. Min Range: -0.2491

Max Act: 0.2176. Min Act: -0.0001

Data Index: 617606 (C4 (Web Text))

Max Activating Token Index: 598

Text #2

Max Range: 0.2491. Min Range: -0.2491

Max Act: 0.2225. Min Act: -0.0001

Data Index: 291714 (C4 (Web Text))

Max Activating Token Index: 584

Text #3

Max Range: 0.2491. Min Range: -0.2491

Max Act: 0.2061. Min Act: -0.0001

Data Index: 1206637 (C4 (Web Text))

Max Activating Token Index: 767

Text #4

Max Range: 0.2491. Min Range: -0.2491

Max Act: 0.1882. Min Act: -0.0001

Data Index: 362293 (C4 (Web Text))

Max Activating Token Index: 913

Text #5

Max Range: 0.2491. Min Range: -0.2491

Max Act: 0.2080. Min Act: -0.0001

Data Index: 313501 (C4 (Web Text))

Max Activating Token Index: 261

Text #6

Max Range: 0.2491. Min Range: -0.2491

Max Act: 0.2003. Min Act: -0.0001

Data Index: 671973 (C4 (Web Text))

Max Activating Token Index: 200

Text #7

Max Range: 0.2491. Min Range: -0.2491

Max Act: 0.1976. Min Act: -0.0001

Data Index: 1080926 (C4 (Web Text))

Max Activating Token Index: 23

Text #8

Max Range: 0.2491. Min Range: -0.2491

Max Act: 0.1974. Min Act: -0.0001

Data Index: 782208 (C4 (Web Text))

Max Activating Token Index: 222

Text #9

Max Range: 0.2491. Min Range: -0.2491

Max Act: 0.1887. Min Act: -0.0001

Data Index: 665291 (C4 (Web Text))

Max Activating Token Index: 927

Text #10

Max Range: 0.2491. Min Range: -0.2491

Max Act: 0.2049. Min Act: -0.0001

Data Index: 581991 (C4 (Web Text))

Max Activating Token Index: 852

Text #11

Max Range: 0.2491. Min Range: -0.2491

Max Act: 0.1805. Min Act: -0.0001

Data Index: 632232 (C4 (Web Text))

Max Activating Token Index: 354

Text #12

Max Range: 0.2491. Min Range: -0.2491

Max Act: 0.1845. Min Act: -0.0001

Data Index: 1287288 (C4 (Web Text))

Max Activating Token Index: 446

Text #13

Max Range: 0.2491. Min Range: -0.2491

Max Act: 0.1866. Min Act: -0.0001

Data Index: 14739 (C4 (Web Text))

Max Activating Token Index: 538

Text #14

Max Range: 0.2491. Min Range: -0.2491

Max Act: 0.1713. Min Act: -0.0001

Data Index: 768020 (C4 (Web Text))

Max Activating Token Index: 963

Text #15

Max Range: 0.2491. Min Range: -0.2491

Max Act: 0.1601. Min Act: -0.0001

Data Index: 721285 (C4 (Web Text))

Max Activating Token Index: 681

Text #16

Max Range: 0.2491. Min Range: -0.2491

Max Act: 0.1732. Min Act: -0.0001

Data Index: 109516 (C4 (Web Text))

Max Activating Token Index: 193

Text #17

Max Range: 0.2491. Min Range: -0.2491

Max Act: 0.1787. Min Act: -0.0001

Data Index: 738917 (C4 (Web Text))

Max Activating Token Index: 504

Text #18

Max Range: 0.2491. Min Range: -0.2491

Max Act: 0.1861. Min Act: -0.0001

Data Index: 714799 (C4 (Web Text))

Max Activating Token Index: 767

Text #19

Max Range: 0.2491. Min Range: -0.2491

Max Act: 0.1786. Min Act: -0.0001

Data Index: 1006634 (C4 (Web Text))

Max Activating Token Index: 402