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

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

Neuron 3597 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7363. Min Range: -0.7363

Max Act: 0.7124. Min Act: -0.0000

Data Index: 509417 (C4 (Web Text))

Max Activating Token Index: 147

Text #1

Max Range: 0.7363. Min Range: -0.7363

Max Act: 0.7183. Min Act: -0.0000

Data Index: 775060 (C4 (Web Text))

Max Activating Token Index: 554

Text #2

Max Range: 0.7363. Min Range: -0.7363

Max Act: 0.6960. Min Act: -0.0000

Data Index: 1313900 (C4 (Web Text))

Max Activating Token Index: 474

Text #3

Max Range: 0.7363. Min Range: -0.7363

Max Act: 0.6440. Min Act: -0.0000

Data Index: 122348 (C4 (Web Text))

Max Activating Token Index: 60

Text #4

Max Range: 0.7363. Min Range: -0.7363

Max Act: 0.7363. Min Act: -0.0000

Data Index: 1272178 (C4 (Web Text))

Max Activating Token Index: 918

Text #5

Max Range: 0.7363. Min Range: -0.7363

Max Act: 0.6813. Min Act: -0.0000

Data Index: 843252 (C4 (Web Text))

Max Activating Token Index: 763

Text #6

Max Range: 0.7363. Min Range: -0.7363

Max Act: 0.6969. Min Act: -0.0000

Data Index: 1186110 (C4 (Web Text))

Max Activating Token Index: 609

Text #7

Max Range: 0.7363. Min Range: -0.7363

Max Act: 0.6735. Min Act: -0.0000

Data Index: 556303 (C4 (Web Text))

Max Activating Token Index: 656

Text #8

Max Range: 0.7363. Min Range: -0.7363

Max Act: 0.6660. Min Act: -0.0000

Data Index: 341945 (C4 (Web Text))

Max Activating Token Index: 132

Text #9

Max Range: 0.7363. Min Range: -0.7363

Max Act: 0.6428. Min Act: -0.0000

Data Index: 313354 (C4 (Web Text))

Max Activating Token Index: 248

Text #10

Max Range: 0.7363. Min Range: -0.7363

Max Act: 0.6427. Min Act: -0.0000

Data Index: 1194141 (C4 (Web Text))

Max Activating Token Index: 25

Text #11

Max Range: 0.7363. Min Range: -0.7363

Max Act: 0.6606. Min Act: -0.0000

Data Index: 643944 (C4 (Web Text))

Max Activating Token Index: 116

Text #12

Max Range: 0.7363. Min Range: -0.7363

Max Act: 0.6562. Min Act: -0.0000

Data Index: 1051745 (C4 (Web Text))

Max Activating Token Index: 551

Text #13

Max Range: 0.7363. Min Range: -0.7363

Max Act: 0.6551. Min Act: -0.0000

Data Index: 126495 (C4 (Web Text))

Max Activating Token Index: 432

Text #14

Max Range: 0.7363. Min Range: -0.7363

Max Act: 0.6293. Min Act: -0.0000

Data Index: 454125 (C4 (Web Text))

Max Activating Token Index: 716

Text #15

Max Range: 0.7363. Min Range: -0.7363

Max Act: 0.6493. Min Act: -0.0000

Data Index: 957666 (C4 (Web Text))

Max Activating Token Index: 913

Text #16

Max Range: 0.7363. Min Range: -0.7363

Max Act: 0.6395. Min Act: -0.0000

Data Index: 265856 (C4 (Web Text))

Max Activating Token Index: 363

Text #17

Max Range: 0.7363. Min Range: -0.7363

Max Act: 0.6305. Min Act: -0.0000

Data Index: 1271384 (C4 (Web Text))

Max Activating Token Index: 194

Text #18

Max Range: 0.7363. Min Range: -0.7363

Max Act: 0.6320. Min Act: -0.0000

Data Index: 817115 (C4 (Web Text))

Max Activating Token Index: 967

Text #19

Max Range: 0.7363. Min Range: -0.7363

Max Act: 0.6504. Min Act: -0.0000

Data Index: 188586 (C4 (Web Text))

Max Activating Token Index: 259