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

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

Neuron 2867 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: 3.0423. Min Range: -3.0423

Max Act: 3.0423. Min Act: -0.0000

Data Index: 814118 (C4 (Web Text))

Max Activating Token Index: 326

Text #1

Max Range: 3.0423. Min Range: -3.0423

Max Act: 2.9092. Min Act: -0.0000

Data Index: 64486 (C4 (Web Text))

Max Activating Token Index: 370

Text #2

Max Range: 3.0423. Min Range: -3.0423

Max Act: 2.6197. Min Act: -0.0000

Data Index: 335521 (C4 (Web Text))

Max Activating Token Index: 432

Text #3

Max Range: 3.0423. Min Range: -3.0423

Max Act: 2.6909. Min Act: -0.0000

Data Index: 713019 (C4 (Web Text))

Max Activating Token Index: 855

Text #4

Max Range: 3.0423. Min Range: -3.0423

Max Act: 2.6033. Min Act: -0.0000

Data Index: 529896 (C4 (Web Text))

Max Activating Token Index: 555

Text #5

Max Range: 3.0423. Min Range: -3.0423

Max Act: 2.4252. Min Act: -0.0000

Data Index: 573600 (C4 (Web Text))

Max Activating Token Index: 67

Text #6

Max Range: 3.0423. Min Range: -3.0423

Max Act: 2.4805. Min Act: -0.0000

Data Index: 1351475 (C4 (Web Text))

Max Activating Token Index: 644

Text #7

Max Range: 3.0423. Min Range: -3.0423

Max Act: 2.3143. Min Act: -0.0000

Data Index: 889159 (C4 (Web Text))

Max Activating Token Index: 646

Text #8

Max Range: 3.0423. Min Range: -3.0423

Max Act: 2.2958. Min Act: -0.0000

Data Index: 1205967 (C4 (Web Text))

Max Activating Token Index: 401

Text #9

Max Range: 3.0423. Min Range: -3.0423

Max Act: 2.4058. Min Act: -0.0000

Data Index: 791741 (C4 (Web Text))

Max Activating Token Index: 596

Text #10

Max Range: 3.0423. Min Range: -3.0423

Max Act: 2.2504. Min Act: -0.0000

Data Index: 991461 (C4 (Web Text))

Max Activating Token Index: 28

Text #11

Max Range: 3.0423. Min Range: -3.0423

Max Act: 2.2363. Min Act: -0.0000

Data Index: 235396 (C4 (Web Text))

Max Activating Token Index: 495

Text #12

Max Range: 3.0423. Min Range: -3.0423

Max Act: 2.1800. Min Act: -0.0000

Data Index: 1316152 (C4 (Web Text))

Max Activating Token Index: 401

Text #13

Max Range: 3.0423. Min Range: -3.0423

Max Act: 2.0466. Min Act: -0.0000

Data Index: 1240588 (C4 (Web Text))

Max Activating Token Index: 784

Text #14

Max Range: 3.0423. Min Range: -3.0423

Max Act: 2.3674. Min Act: -0.0000

Data Index: 173600 (C4 (Web Text))

Max Activating Token Index: 372

Text #15

Max Range: 3.0423. Min Range: -3.0423

Max Act: 2.0964. Min Act: -0.0000

Data Index: 43212 (C4 (Web Text))

Max Activating Token Index: 375

Text #16

Max Range: 3.0423. Min Range: -3.0423

Max Act: 2.2134. Min Act: -0.0000

Data Index: 513567 (C4 (Web Text))

Max Activating Token Index: 912

Text #17

Max Range: 3.0423. Min Range: -3.0423

Max Act: 2.3002. Min Act: -0.0000

Data Index: 400716 (C4 (Web Text))

Max Activating Token Index: 356

Text #18

Max Range: 3.0423. Min Range: -3.0423

Max Act: 2.1397. Min Act: -0.0000

Data Index: 577011 (C4 (Web Text))

Max Activating Token Index: 159

Text #19

Max Range: 3.0423. Min Range: -3.0423

Max Act: 2.1423. Min Act: -0.0000

Data Index: 903726 (C4 (Web Text))

Max Activating Token Index: 684