Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2811 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.6444. Min Range: -0.6444

Max Act: 0.6444. Min Act: -0.0001

Data Index: 532218 (C4 (Web Text))

Max Activating Token Index: 668

Text #1

Max Range: 0.6444. Min Range: -0.6444

Max Act: 0.5707. Min Act: -0.0001

Data Index: 1268882 (C4 (Web Text))

Max Activating Token Index: 610

Text #2

Max Range: 0.6444. Min Range: -0.6444

Max Act: 0.5731. Min Act: -0.0001

Data Index: 795079 (C4 (Web Text))

Max Activating Token Index: 599

Text #3

Max Range: 0.6444. Min Range: -0.6444

Max Act: 0.5225. Min Act: -0.0001

Data Index: 23428 (C4 (Web Text))

Max Activating Token Index: 656

Text #4

Max Range: 0.6444. Min Range: -0.6444

Max Act: 0.5133. Min Act: -0.0000

Data Index: 1136089 (C4 (Web Text))

Max Activating Token Index: 156

Text #5

Max Range: 0.6444. Min Range: -0.6444

Max Act: 0.5044. Min Act: -0.0000

Data Index: 1148976 (C4 (Web Text))

Max Activating Token Index: 574

Text #6

Max Range: 0.6444. Min Range: -0.6444

Max Act: 0.4974. Min Act: -0.0000

Data Index: 625442 (C4 (Web Text))

Max Activating Token Index: 405

Text #7

Max Range: 0.6444. Min Range: -0.6444

Max Act: 0.4897. Min Act: -0.0001

Data Index: 52342 (C4 (Web Text))

Max Activating Token Index: 25

Text #8

Max Range: 0.6444. Min Range: -0.6444

Max Act: 0.4825. Min Act: -0.0000

Data Index: 1186463 (C4 (Web Text))

Max Activating Token Index: 744

Text #9

Max Range: 0.6444. Min Range: -0.6444

Max Act: 0.4667. Min Act: -0.0000

Data Index: 1007612 (C4 (Web Text))

Max Activating Token Index: 89

Text #10

Max Range: 0.6444. Min Range: -0.6444

Max Act: 0.4815. Min Act: -0.0000

Data Index: 691955 (C4 (Web Text))

Max Activating Token Index: 100

Text #11

Max Range: 0.6444. Min Range: -0.6444

Max Act: 0.4650. Min Act: -0.0000

Data Index: 597131 (C4 (Web Text))

Max Activating Token Index: 575

Text #12

Max Range: 0.6444. Min Range: -0.6444

Max Act: 0.4799. Min Act: -0.0000

Data Index: 298225 (C4 (Web Text))

Max Activating Token Index: 830

Text #13

Max Range: 0.6444. Min Range: -0.6444

Max Act: 0.5136. Min Act: -0.0000

Data Index: 500642 (C4 (Web Text))

Max Activating Token Index: 344

Text #14

Max Range: 0.6444. Min Range: -0.6444

Max Act: 0.4710. Min Act: -0.0000

Data Index: 138730 (C4 (Web Text))

Max Activating Token Index: 433

Text #15

Max Range: 0.6444. Min Range: -0.6444

Max Act: 0.4506. Min Act: -0.0000

Data Index: 967944 (C4 (Web Text))

Max Activating Token Index: 859

Text #16

Max Range: 0.6444. Min Range: -0.6444

Max Act: 0.4517. Min Act: -0.0000

Data Index: 299179 (C4 (Web Text))

Max Activating Token Index: 881

Text #17

Max Range: 0.6444. Min Range: -0.6444

Max Act: 0.4699. Min Act: -0.0000

Data Index: 550696 (C4 (Web Text))

Max Activating Token Index: 51

Text #18

Max Range: 0.6444. Min Range: -0.6444

Max Act: 0.4372. Min Act: -0.0000

Data Index: 9860 (C4 (Web Text))

Max Activating Token Index: 753

Text #19

Max Range: 0.6444. Min Range: -0.6444

Max Act: 0.4280. Min Act: -0.0000

Data Index: 553028 (C4 (Web Text))

Max Activating Token Index: 770