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

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

Neuron 1831 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: 2.0762. Min Range: -2.0762

Max Act: 2.0762. Min Act: -0.0000

Data Index: 1614556 (Python Code)

Max Activating Token Index: 12

Text #1

Max Range: 2.0762. Min Range: -2.0762

Max Act: 1.7972. Min Act: -0.0000

Data Index: 1377664 (Python Code)

Max Activating Token Index: 94

Text #2

Max Range: 2.0762. Min Range: -2.0762

Max Act: 1.6510. Min Act: -0.0000

Data Index: 1377853 (Python Code)

Max Activating Token Index: 222

Text #3

Max Range: 2.0762. Min Range: -2.0762

Max Act: 1.8587. Min Act: -0.0000

Data Index: 1125163 (C4 (Web Text))

Max Activating Token Index: 747

Text #4

Max Range: 2.0762. Min Range: -2.0762

Max Act: 1.6964. Min Act: -0.0000

Data Index: 1401359 (Python Code)

Max Activating Token Index: 696

Text #5

Max Range: 2.0762. Min Range: -2.0762

Max Act: 1.6848. Min Act: -0.0000

Data Index: 1568257 (Python Code)

Max Activating Token Index: 7

Text #6

Max Range: 2.0762. Min Range: -2.0762

Max Act: 1.6263. Min Act: -0.0000

Data Index: 1123631 (C4 (Web Text))

Max Activating Token Index: 705

Text #7

Max Range: 2.0762. Min Range: -2.0762

Max Act: 1.6097. Min Act: -0.0000

Data Index: 1205401 (C4 (Web Text))

Max Activating Token Index: 43

Text #8

Max Range: 2.0762. Min Range: -2.0762

Max Act: 1.7107. Min Act: -0.0000

Data Index: 319468 (C4 (Web Text))

Max Activating Token Index: 109

Text #9

Max Range: 2.0762. Min Range: -2.0762

Max Act: 1.4408. Min Act: -0.0000

Data Index: 1428460 (Python Code)

Max Activating Token Index: 14

Text #10

Max Range: 2.0762. Min Range: -2.0762

Max Act: 1.5661. Min Act: -0.0000

Data Index: 1503234 (Python Code)

Max Activating Token Index: 168

Text #11

Max Range: 2.0762. Min Range: -2.0762

Max Act: 1.5692. Min Act: -0.0000

Data Index: 1585359 (Python Code)

Max Activating Token Index: 529

Text #12

Max Range: 2.0762. Min Range: -2.0762

Max Act: 1.5441. Min Act: -0.0000

Data Index: 1365992 (Python Code)

Max Activating Token Index: 80

Text #13

Max Range: 2.0762. Min Range: -2.0762

Max Act: 1.5457. Min Act: -0.0000

Data Index: 1289313 (C4 (Web Text))

Max Activating Token Index: 388

Text #14

Max Range: 2.0762. Min Range: -2.0762

Max Act: 1.3790. Min Act: -0.0000

Data Index: 1467633 (Python Code)

Max Activating Token Index: 113

Text #15

Max Range: 2.0762. Min Range: -2.0762

Max Act: 1.4531. Min Act: -0.0000

Data Index: 1107969 (C4 (Web Text))

Max Activating Token Index: 484

Text #16

Max Range: 2.0762. Min Range: -2.0762

Max Act: 1.5495. Min Act: -0.0000

Data Index: 763968 (C4 (Web Text))

Max Activating Token Index: 795

Text #17

Max Range: 2.0762. Min Range: -2.0762

Max Act: 1.4442. Min Act: -0.0000

Data Index: 885771 (C4 (Web Text))

Max Activating Token Index: 661

Text #18

Max Range: 2.0762. Min Range: -2.0762

Max Act: 1.5301. Min Act: -0.0000

Data Index: 540391 (C4 (Web Text))

Max Activating Token Index: 503

Text #19

Max Range: 2.0762. Min Range: -2.0762

Max Act: 1.5195. Min Act: -0.0000

Data Index: 1372274 (Python Code)

Max Activating Token Index: 648