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

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

Neuron 2891 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9502. Min Range: -0.9502

Max Act: 0.9502. Min Act: -0.0000

Data Index: 744469 (C4 (Web Text))

Max Activating Token Index: 899

Text #1

Max Range: 0.9502. Min Range: -0.9502

Max Act: 0.8812. Min Act: -0.0000

Data Index: 1248906 (C4 (Web Text))

Max Activating Token Index: 583

Text #2

Max Range: 0.9502. Min Range: -0.9502

Max Act: 0.8549. Min Act: -0.0000

Data Index: 1271448 (C4 (Web Text))

Max Activating Token Index: 115

Text #3

Max Range: 0.9502. Min Range: -0.9502

Max Act: 0.8015. Min Act: -0.0001

Data Index: 1312328 (C4 (Web Text))

Max Activating Token Index: 135

Text #4

Max Range: 0.9502. Min Range: -0.9502

Max Act: 0.7697. Min Act: -0.0000

Data Index: 197168 (C4 (Web Text))

Max Activating Token Index: 963

Text #5

Max Range: 0.9502. Min Range: -0.9502

Max Act: 0.7423. Min Act: -0.0000

Data Index: 1226014 (C4 (Web Text))

Max Activating Token Index: 553

Text #6

Max Range: 0.9502. Min Range: -0.9502

Max Act: 0.6509. Min Act: -0.0000

Data Index: 104189 (C4 (Web Text))

Max Activating Token Index: 158

Text #7

Max Range: 0.9502. Min Range: -0.9502

Max Act: 0.7386. Min Act: -0.0001

Data Index: 683683 (C4 (Web Text))

Max Activating Token Index: 385

Text #8

Max Range: 0.9502. Min Range: -0.9502

Max Act: 0.6860. Min Act: -0.0001

Data Index: 344115 (C4 (Web Text))

Max Activating Token Index: 953

Text #9

Max Range: 0.9502. Min Range: -0.9502

Max Act: 0.7012. Min Act: -0.0001

Data Index: 1214222 (C4 (Web Text))

Max Activating Token Index: 1001

Text #10

Max Range: 0.9502. Min Range: -0.9502

Max Act: 0.6451. Min Act: -0.0000

Data Index: 1037135 (C4 (Web Text))

Max Activating Token Index: 492

Text #11

Max Range: 0.9502. Min Range: -0.9502

Max Act: 0.7318. Min Act: -0.0001

Data Index: 289412 (C4 (Web Text))

Max Activating Token Index: 560

Text #12

Max Range: 0.9502. Min Range: -0.9502

Max Act: 0.6400. Min Act: -0.0000

Data Index: 1218731 (C4 (Web Text))

Max Activating Token Index: 419

Text #13

Max Range: 0.9502. Min Range: -0.9502

Max Act: 0.6376. Min Act: -0.0001

Data Index: 655365 (C4 (Web Text))

Max Activating Token Index: 485

Text #14

Max Range: 0.9502. Min Range: -0.9502

Max Act: 0.5896. Min Act: -0.0001

Data Index: 796928 (C4 (Web Text))

Max Activating Token Index: 732

Text #15

Max Range: 0.9502. Min Range: -0.9502

Max Act: 0.7337. Min Act: -0.0000

Data Index: 590475 (C4 (Web Text))

Max Activating Token Index: 782

Text #16

Max Range: 0.9502. Min Range: -0.9502

Max Act: 0.6768. Min Act: -0.0000

Data Index: 969966 (C4 (Web Text))

Max Activating Token Index: 118

Text #17

Max Range: 0.9502. Min Range: -0.9502

Max Act: 0.6544. Min Act: -0.0000

Data Index: 1266062 (C4 (Web Text))

Max Activating Token Index: 656

Text #18

Max Range: 0.9502. Min Range: -0.9502

Max Act: 0.6145. Min Act: -0.0001

Data Index: 456326 (C4 (Web Text))

Max Activating Token Index: 262

Text #19

Max Range: 0.9502. Min Range: -0.9502

Max Act: 0.6069. Min Act: -0.0000

Data Index: 151989 (C4 (Web Text))

Max Activating Token Index: 24