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

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

Neuron 263 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6750. Min Range: -1.6750

Max Act: 1.6750. Min Act: 0.0001

Data Index: 677438 (C4 (Web Text))

Max Activating Token Index: 77

Text #1

Max Range: 1.6750. Min Range: -1.6750

Max Act: 1.5505. Min Act: -0.0000

Data Index: 1268597 (C4 (Web Text))

Max Activating Token Index: 154

Text #2

Max Range: 1.6750. Min Range: -1.6750

Max Act: 1.6282. Min Act: -0.0000

Data Index: 1170983 (C4 (Web Text))

Max Activating Token Index: 882

Text #3

Max Range: 1.6750. Min Range: -1.6750

Max Act: 1.4973. Min Act: -0.0000

Data Index: 318805 (C4 (Web Text))

Max Activating Token Index: 398

Text #4

Max Range: 1.6750. Min Range: -1.6750

Max Act: 1.4797. Min Act: -0.0000

Data Index: 536117 (C4 (Web Text))

Max Activating Token Index: 853

Text #5

Max Range: 1.6750. Min Range: -1.6750

Max Act: 1.3874. Min Act: -0.0000

Data Index: 268298 (C4 (Web Text))

Max Activating Token Index: 795

Text #6

Max Range: 1.6750. Min Range: -1.6750

Max Act: 1.5248. Min Act: 0.0000

Data Index: 1222528 (C4 (Web Text))

Max Activating Token Index: 11

Text #7

Max Range: 1.6750. Min Range: -1.6750

Max Act: 1.3429. Min Act: -0.0000

Data Index: 165077 (C4 (Web Text))

Max Activating Token Index: 1016

Text #8

Max Range: 1.6750. Min Range: -1.6750

Max Act: 1.3998. Min Act: -0.0000

Data Index: 1098332 (C4 (Web Text))

Max Activating Token Index: 157

Text #9

Max Range: 1.6750. Min Range: -1.6750

Max Act: 1.3342. Min Act: -0.0000

Data Index: 786070 (C4 (Web Text))

Max Activating Token Index: 663

Text #10

Max Range: 1.6750. Min Range: -1.6750

Max Act: 1.1341. Min Act: -0.0000

Data Index: 3506 (C4 (Web Text))

Max Activating Token Index: 269

Text #11

Max Range: 1.6750. Min Range: -1.6750

Max Act: 1.2562. Min Act: -0.0000

Data Index: 383169 (C4 (Web Text))

Max Activating Token Index: 137

Text #12

Max Range: 1.6750. Min Range: -1.6750

Max Act: 1.3328. Min Act: -0.0000

Data Index: 790374 (C4 (Web Text))

Max Activating Token Index: 662

Text #13

Max Range: 1.6750. Min Range: -1.6750

Max Act: 1.3291. Min Act: -0.0000

Data Index: 585075 (C4 (Web Text))

Max Activating Token Index: 956

Text #14

Max Range: 1.6750. Min Range: -1.6750

Max Act: 1.2421. Min Act: -0.0000

Data Index: 1338113 (C4 (Web Text))

Max Activating Token Index: 287

Text #15

Max Range: 1.6750. Min Range: -1.6750

Max Act: 1.2372. Min Act: -0.0000

Data Index: 507217 (C4 (Web Text))

Max Activating Token Index: 692

Text #16

Max Range: 1.6750. Min Range: -1.6750

Max Act: 1.3166. Min Act: -0.0000

Data Index: 939305 (C4 (Web Text))

Max Activating Token Index: 4

Text #17

Max Range: 1.6750. Min Range: -1.6750

Max Act: 1.1655. Min Act: -0.0000

Data Index: 272186 (C4 (Web Text))

Max Activating Token Index: 250

Text #18

Max Range: 1.6750. Min Range: -1.6750

Max Act: 1.1634. Min Act: -0.0000

Data Index: 554142 (C4 (Web Text))

Max Activating Token Index: 4

Text #19

Max Range: 1.6750. Min Range: -1.6750

Max Act: 1.2082. Min Act: -0.0000

Data Index: 776816 (C4 (Web Text))

Max Activating Token Index: 176