Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 593 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.4656. Min Range: -0.4656

Max Act: 0.4656. Min Act: -0.0001

Data Index: 1451316 (Python Code)

Max Activating Token Index: 597

Text #1

Max Range: 0.4656. Min Range: -0.4656

Max Act: 0.4401. Min Act: -0.0001

Data Index: 1431150 (Python Code)

Max Activating Token Index: 489

Text #2

Max Range: 0.4656. Min Range: -0.4656

Max Act: 0.4512. Min Act: -0.0001

Data Index: 1450248 (Python Code)

Max Activating Token Index: 697

Text #3

Max Range: 0.4656. Min Range: -0.4656

Max Act: 0.4174. Min Act: -0.0001

Data Index: 1552635 (Python Code)

Max Activating Token Index: 233

Text #4

Max Range: 0.4656. Min Range: -0.4656

Max Act: 0.4194. Min Act: -0.0001

Data Index: 1536937 (Python Code)

Max Activating Token Index: 314

Text #5

Max Range: 0.4656. Min Range: -0.4656

Max Act: 0.4622. Min Act: -0.0001

Data Index: 1373996 (Python Code)

Max Activating Token Index: 182

Text #6

Max Range: 0.4656. Min Range: -0.4656

Max Act: 0.3088. Min Act: -0.0001

Data Index: 1502494 (Python Code)

Max Activating Token Index: 833

Text #7

Max Range: 0.4656. Min Range: -0.4656

Max Act: 0.3010. Min Act: -0.0000

Data Index: 1314599 (C4 (Web Text))

Max Activating Token Index: 387

Text #8

Max Range: 0.4656. Min Range: -0.4656

Max Act: 0.2918. Min Act: -0.0000

Data Index: 233737 (C4 (Web Text))

Max Activating Token Index: 535

Text #9

Max Range: 0.4656. Min Range: -0.4656

Max Act: 0.2759. Min Act: -0.0000

Data Index: 279791 (C4 (Web Text))

Max Activating Token Index: 845

Text #10

Max Range: 0.4656. Min Range: -0.4656

Max Act: 0.2549. Min Act: -0.0000

Data Index: 900306 (C4 (Web Text))

Max Activating Token Index: 152

Text #11

Max Range: 0.4656. Min Range: -0.4656

Max Act: 0.2457. Min Act: -0.0000

Data Index: 290053 (C4 (Web Text))

Max Activating Token Index: 48

Text #12

Max Range: 0.4656. Min Range: -0.4656

Max Act: 0.2421. Min Act: -0.0000

Data Index: 1427732 (Python Code)

Max Activating Token Index: 38

Text #13

Max Range: 0.4656. Min Range: -0.4656

Max Act: 0.2303. Min Act: -0.0000

Data Index: 1358950 (C4 (Web Text))

Max Activating Token Index: 492

Text #14

Max Range: 0.4656. Min Range: -0.4656

Max Act: 0.2195. Min Act: -0.0000

Data Index: 190928 (C4 (Web Text))

Max Activating Token Index: 646

Text #15

Max Range: 0.4656. Min Range: -0.4656

Max Act: 0.2208. Min Act: -0.0000

Data Index: 902338 (C4 (Web Text))

Max Activating Token Index: 385

Text #16

Max Range: 0.4656. Min Range: -0.4656

Max Act: 0.2298. Min Act: -0.0000

Data Index: 865969 (C4 (Web Text))

Max Activating Token Index: 990

Text #17

Max Range: 0.4656. Min Range: -0.4656

Max Act: 0.2225. Min Act: -0.0000

Data Index: 786102 (C4 (Web Text))

Max Activating Token Index: 644

Text #18

Max Range: 0.4656. Min Range: -0.4656

Max Act: 0.2257. Min Act: -0.0000

Data Index: 842321 (C4 (Web Text))

Max Activating Token Index: 352

Text #19

Max Range: 0.4656. Min Range: -0.4656

Max Act: 0.2242. Min Act: -0.0000

Data Index: 1001622 (C4 (Web Text))

Max Activating Token Index: 795