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

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

Neuron 297 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7422. Min Range: -0.7422

Max Act: 0.7422. Min Act: -0.0001

Data Index: 437853 (C4 (Web Text))

Max Activating Token Index: 343

Text #1

Max Range: 0.7422. Min Range: -0.7422

Max Act: 0.6462. Min Act: -0.0001

Data Index: 158829 (C4 (Web Text))

Max Activating Token Index: 280

Text #2

Max Range: 0.7422. Min Range: -0.7422

Max Act: 0.5285. Min Act: -0.0001

Data Index: 144645 (C4 (Web Text))

Max Activating Token Index: 506

Text #3

Max Range: 0.7422. Min Range: -0.7422

Max Act: 0.5419. Min Act: -0.0000

Data Index: 1039433 (C4 (Web Text))

Max Activating Token Index: 980

Text #4

Max Range: 0.7422. Min Range: -0.7422

Max Act: 0.5137. Min Act: -0.0001

Data Index: 1184637 (C4 (Web Text))

Max Activating Token Index: 125

Text #5

Max Range: 0.7422. Min Range: -0.7422

Max Act: 0.5254. Min Act: -0.0001

Data Index: 598259 (C4 (Web Text))

Max Activating Token Index: 773

Text #6

Max Range: 0.7422. Min Range: -0.7422

Max Act: 0.5003. Min Act: -0.0001

Data Index: 276367 (C4 (Web Text))

Max Activating Token Index: 881

Text #7

Max Range: 0.7422. Min Range: -0.7422

Max Act: 0.4837. Min Act: -0.0000

Data Index: 44981 (C4 (Web Text))

Max Activating Token Index: 420

Text #8

Max Range: 0.7422. Min Range: -0.7422

Max Act: 0.4829. Min Act: -0.0001

Data Index: 1047151 (C4 (Web Text))

Max Activating Token Index: 608

Text #9

Max Range: 0.7422. Min Range: -0.7422

Max Act: 0.4746. Min Act: -0.0000

Data Index: 47888 (C4 (Web Text))

Max Activating Token Index: 998

Text #10

Max Range: 0.7422. Min Range: -0.7422

Max Act: 0.5146. Min Act: -0.0001

Data Index: 137963 (C4 (Web Text))

Max Activating Token Index: 642

Text #11

Max Range: 0.7422. Min Range: -0.7422

Max Act: 0.4373. Min Act: -0.0001

Data Index: 468224 (C4 (Web Text))

Max Activating Token Index: 267

Text #12

Max Range: 0.7422. Min Range: -0.7422

Max Act: 0.4239. Min Act: -0.0001

Data Index: 1095438 (C4 (Web Text))

Max Activating Token Index: 863

Text #13

Max Range: 0.7422. Min Range: -0.7422

Max Act: 0.4634. Min Act: -0.0000

Data Index: 473282 (C4 (Web Text))

Max Activating Token Index: 1014

Text #14

Max Range: 0.7422. Min Range: -0.7422

Max Act: 0.4775. Min Act: -0.0001

Data Index: 84351 (C4 (Web Text))

Max Activating Token Index: 913

Text #15

Max Range: 0.7422. Min Range: -0.7422

Max Act: 0.4733. Min Act: -0.0001

Data Index: 220737 (C4 (Web Text))

Max Activating Token Index: 761

Text #16

Max Range: 0.7422. Min Range: -0.7422

Max Act: 0.4451. Min Act: -0.0001

Data Index: 118891 (C4 (Web Text))

Max Activating Token Index: 35

Text #17

Max Range: 0.7422. Min Range: -0.7422

Max Act: 0.4602. Min Act: -0.0001

Data Index: 30509 (C4 (Web Text))

Max Activating Token Index: 964

Text #18

Max Range: 0.7422. Min Range: -0.7422

Max Act: 0.4206. Min Act: -0.0000

Data Index: 898725 (C4 (Web Text))

Max Activating Token Index: 602

Text #19

Max Range: 0.7422. Min Range: -0.7422

Max Act: 0.4280. Min Act: -0.0001

Data Index: 652764 (C4 (Web Text))

Max Activating Token Index: 48