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

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

Neuron 3154 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.4238. Min Range: -1.4238

Max Act: 1.4238. Min Act: -0.0000

Data Index: 1116443 (C4 (Web Text))

Max Activating Token Index: 281

Text #1

Max Range: 1.4238. Min Range: -1.4238

Max Act: 0.9356. Min Act: -0.0000

Data Index: 88937 (C4 (Web Text))

Max Activating Token Index: 619

Text #2

Max Range: 1.4238. Min Range: -1.4238

Max Act: 0.9167. Min Act: -0.0000

Data Index: 623046 (C4 (Web Text))

Max Activating Token Index: 185

Text #3

Max Range: 1.4238. Min Range: -1.4238

Max Act: 0.8323. Min Act: -0.0000

Data Index: 803241 (C4 (Web Text))

Max Activating Token Index: 375

Text #4

Max Range: 1.4238. Min Range: -1.4238

Max Act: 0.7822. Min Act: -0.0000

Data Index: 945765 (C4 (Web Text))

Max Activating Token Index: 168

Text #5

Max Range: 1.4238. Min Range: -1.4238

Max Act: 0.6955. Min Act: -0.0000

Data Index: 117868 (C4 (Web Text))

Max Activating Token Index: 879

Text #6

Max Range: 1.4238. Min Range: -1.4238

Max Act: 0.6177. Min Act: -0.0000

Data Index: 40682 (C4 (Web Text))

Max Activating Token Index: 587

Text #7

Max Range: 1.4238. Min Range: -1.4238

Max Act: 0.5953. Min Act: -0.0000

Data Index: 435943 (C4 (Web Text))

Max Activating Token Index: 1000

Text #8

Max Range: 1.4238. Min Range: -1.4238

Max Act: 0.5655. Min Act: -0.0000

Data Index: 944783 (C4 (Web Text))

Max Activating Token Index: 545

Text #9

Max Range: 1.4238. Min Range: -1.4238

Max Act: 0.5262. Min Act: -0.0000

Data Index: 519000 (C4 (Web Text))

Max Activating Token Index: 705

Text #10

Max Range: 1.4238. Min Range: -1.4238

Max Act: 0.5373. Min Act: -0.0000

Data Index: 824453 (C4 (Web Text))

Max Activating Token Index: 699

Text #11

Max Range: 1.4238. Min Range: -1.4238

Max Act: 0.5305. Min Act: -0.0000

Data Index: 715589 (C4 (Web Text))

Max Activating Token Index: 154

Text #12

Max Range: 1.4238. Min Range: -1.4238

Max Act: 0.5116. Min Act: -0.0000

Data Index: 789262 (C4 (Web Text))

Max Activating Token Index: 232

Text #13

Max Range: 1.4238. Min Range: -1.4238

Max Act: 0.5003. Min Act: -0.0000

Data Index: 104482 (C4 (Web Text))

Max Activating Token Index: 353

Text #14

Max Range: 1.4238. Min Range: -1.4238

Max Act: 0.5309. Min Act: -0.0000

Data Index: 13233 (C4 (Web Text))

Max Activating Token Index: 339

Text #15

Max Range: 1.4238. Min Range: -1.4238

Max Act: 0.4823. Min Act: -0.0000

Data Index: 447864 (C4 (Web Text))

Max Activating Token Index: 498

Text #16

Max Range: 1.4238. Min Range: -1.4238

Max Act: 0.4809. Min Act: -0.0000

Data Index: 1225671 (C4 (Web Text))

Max Activating Token Index: 166

Text #17

Max Range: 1.4238. Min Range: -1.4238

Max Act: 0.4694. Min Act: -0.0000

Data Index: 138031 (C4 (Web Text))

Max Activating Token Index: 151

Text #18

Max Range: 1.4238. Min Range: -1.4238

Max Act: 0.4505. Min Act: -0.0000

Data Index: 837924 (C4 (Web Text))

Max Activating Token Index: 270

Text #19

Max Range: 1.4238. Min Range: -1.4238

Max Act: 0.4670. Min Act: 0.0000

Data Index: 150402 (C4 (Web Text))

Max Activating Token Index: 643