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

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

Neuron 641 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4869. Min Range: -0.4869

Max Act: 0.4869. Min Act: -0.0001

Data Index: 65957 (C4 (Web Text))

Max Activating Token Index: 688

Text #1

Max Range: 0.4869. Min Range: -0.4869

Max Act: 0.4858. Min Act: -0.0001

Data Index: 544431 (C4 (Web Text))

Max Activating Token Index: 459

Text #2

Max Range: 0.4869. Min Range: -0.4869

Max Act: 0.4491. Min Act: -0.0001

Data Index: 1126604 (C4 (Web Text))

Max Activating Token Index: 487

Text #3

Max Range: 0.4869. Min Range: -0.4869

Max Act: 0.4723. Min Act: -0.0001

Data Index: 385847 (C4 (Web Text))

Max Activating Token Index: 477

Text #4

Max Range: 0.4869. Min Range: -0.4869

Max Act: 0.4451. Min Act: -0.0001

Data Index: 1253043 (C4 (Web Text))

Max Activating Token Index: 411

Text #5

Max Range: 0.4869. Min Range: -0.4869

Max Act: 0.4554. Min Act: -0.0001

Data Index: 424684 (C4 (Web Text))

Max Activating Token Index: 444

Text #6

Max Range: 0.4869. Min Range: -0.4869

Max Act: 0.4376. Min Act: -0.0001

Data Index: 234266 (C4 (Web Text))

Max Activating Token Index: 795

Text #7

Max Range: 0.4869. Min Range: -0.4869

Max Act: 0.4550. Min Act: -0.0001

Data Index: 1136140 (C4 (Web Text))

Max Activating Token Index: 448

Text #8

Max Range: 0.4869. Min Range: -0.4869

Max Act: 0.4365. Min Act: -0.0001

Data Index: 784780 (C4 (Web Text))

Max Activating Token Index: 729

Text #9

Max Range: 0.4869. Min Range: -0.4869

Max Act: 0.4181. Min Act: -0.0001

Data Index: 405431 (C4 (Web Text))

Max Activating Token Index: 138

Text #10

Max Range: 0.4869. Min Range: -0.4869

Max Act: 0.4163. Min Act: -0.0001

Data Index: 662794 (C4 (Web Text))

Max Activating Token Index: 210

Text #11

Max Range: 0.4869. Min Range: -0.4869

Max Act: 0.4140. Min Act: -0.0001

Data Index: 334453 (C4 (Web Text))

Max Activating Token Index: 250

Text #12

Max Range: 0.4869. Min Range: -0.4869

Max Act: 0.4568. Min Act: -0.0001

Data Index: 1050080 (C4 (Web Text))

Max Activating Token Index: 809

Text #13

Max Range: 0.4869. Min Range: -0.4869

Max Act: 0.4412. Min Act: -0.0001

Data Index: 143799 (C4 (Web Text))

Max Activating Token Index: 593

Text #14

Max Range: 0.4869. Min Range: -0.4869

Max Act: 0.4219. Min Act: -0.0001

Data Index: 910523 (C4 (Web Text))

Max Activating Token Index: 937

Text #15

Max Range: 0.4869. Min Range: -0.4869

Max Act: 0.4308. Min Act: -0.0001

Data Index: 945850 (C4 (Web Text))

Max Activating Token Index: 15

Text #16

Max Range: 0.4869. Min Range: -0.4869

Max Act: 0.4123. Min Act: -0.0001

Data Index: 872566 (C4 (Web Text))

Max Activating Token Index: 482

Text #17

Max Range: 0.4869. Min Range: -0.4869

Max Act: 0.3970. Min Act: -0.0001

Data Index: 1337071 (C4 (Web Text))

Max Activating Token Index: 694

Text #18

Max Range: 0.4869. Min Range: -0.4869

Max Act: 0.3951. Min Act: -0.0001

Data Index: 835270 (C4 (Web Text))

Max Activating Token Index: 333

Text #19

Max Range: 0.4869. Min Range: -0.4869

Max Act: 0.3913. Min Act: -0.0001

Data Index: 1518882 (Python Code)

Max Activating Token Index: 873