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

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

Neuron 2708 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: 1.4544. Min Range: -1.4544

Max Act: 1.4544. Min Act: -0.0000

Data Index: 1599672 (Python Code)

Max Activating Token Index: 539

Text #1

Max Range: 1.4544. Min Range: -1.4544

Max Act: 1.2203. Min Act: 0.0000

Data Index: 1583701 (Python Code)

Max Activating Token Index: 802

Text #2

Max Range: 1.4544. Min Range: -1.4544

Max Act: 1.2371. Min Act: 0.0000

Data Index: 1403764 (Python Code)

Max Activating Token Index: 136

Text #3

Max Range: 1.4544. Min Range: -1.4544

Max Act: 1.1505. Min Act: -0.0000

Data Index: 1516128 (Python Code)

Max Activating Token Index: 912

Text #4

Max Range: 1.4544. Min Range: -1.4544

Max Act: 1.2899. Min Act: 0.0000

Data Index: 1453337 (Python Code)

Max Activating Token Index: 888

Text #5

Max Range: 1.4544. Min Range: -1.4544

Max Act: 1.1346. Min Act: 0.0000

Data Index: 1519476 (Python Code)

Max Activating Token Index: 573

Text #6

Max Range: 1.4544. Min Range: -1.4544

Max Act: 1.1139. Min Act: 0.0000

Data Index: 1597969 (Python Code)

Max Activating Token Index: 327

Text #7

Max Range: 1.4544. Min Range: -1.4544

Max Act: 1.0365. Min Act: 0.0000

Data Index: 1519150 (Python Code)

Max Activating Token Index: 601

Text #8

Max Range: 1.4544. Min Range: -1.4544

Max Act: 1.1086. Min Act: -0.0000

Data Index: 1427277 (Python Code)

Max Activating Token Index: 564

Text #9

Max Range: 1.4544. Min Range: -1.4544

Max Act: 1.0502. Min Act: 0.0000

Data Index: 1445191 (Python Code)

Max Activating Token Index: 83

Text #10

Max Range: 1.4544. Min Range: -1.4544

Max Act: 0.9883. Min Act: -0.0000

Data Index: 1639291 (Python Code)

Max Activating Token Index: 429

Text #11

Max Range: 1.4544. Min Range: -1.4544

Max Act: 1.1068. Min Act: -0.0000

Data Index: 1482904 (Python Code)

Max Activating Token Index: 1014

Text #12

Max Range: 1.4544. Min Range: -1.4544

Max Act: 1.0344. Min Act: -0.0000

Data Index: 1463146 (Python Code)

Max Activating Token Index: 132

Text #13

Max Range: 1.4544. Min Range: -1.4544

Max Act: 0.9707. Min Act: 0.0000

Data Index: 1480376 (Python Code)

Max Activating Token Index: 327

Text #14

Max Range: 1.4544. Min Range: -1.4544

Max Act: 1.0976. Min Act: -0.0000

Data Index: 1467913 (Python Code)

Max Activating Token Index: 94

Text #15

Max Range: 1.4544. Min Range: -1.4544

Max Act: 1.0732. Min Act: 0.0000

Data Index: 1463741 (Python Code)

Max Activating Token Index: 340

Text #16

Max Range: 1.4544. Min Range: -1.4544

Max Act: 1.0622. Min Act: -0.0000

Data Index: 1649362 (Python Code)

Max Activating Token Index: 586

Text #17

Max Range: 1.4544. Min Range: -1.4544

Max Act: 1.0509. Min Act: 0.0000

Data Index: 1642403 (Python Code)

Max Activating Token Index: 187

Text #18

Max Range: 1.4544. Min Range: -1.4544

Max Act: 1.2601. Min Act: 0.0000

Data Index: 1572979 (Python Code)

Max Activating Token Index: 269

Text #19

Max Range: 1.4544. Min Range: -1.4544

Max Act: 1.0511. Min Act: 0.0000

Data Index: 1478967 (Python Code)

Max Activating Token Index: 541