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

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

Neuron 4376 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6587. Min Range: -0.6587

Max Act: 0.6550. Min Act: -0.0001

Data Index: 1438853 (Python Code)

Max Activating Token Index: 210

Text #1

Max Range: 0.6587. Min Range: -0.6587

Max Act: 0.6298. Min Act: -0.0001

Data Index: 1392431 (Python Code)

Max Activating Token Index: 755

Text #2

Max Range: 0.6587. Min Range: -0.6587

Max Act: 0.5712. Min Act: -0.0001

Data Index: 1606743 (Python Code)

Max Activating Token Index: 718

Text #3

Max Range: 0.6587. Min Range: -0.6587

Max Act: 0.5432. Min Act: -0.0001

Data Index: 1553006 (Python Code)

Max Activating Token Index: 620

Text #4

Max Range: 0.6587. Min Range: -0.6587

Max Act: 0.6032. Min Act: -0.0001

Data Index: 1363941 (Python Code)

Max Activating Token Index: 515

Text #5

Max Range: 0.6587. Min Range: -0.6587

Max Act: 0.4898. Min Act: -0.0001

Data Index: 1376888 (Python Code)

Max Activating Token Index: 214

Text #6

Max Range: 0.6587. Min Range: -0.6587

Max Act: 0.5666. Min Act: -0.0001

Data Index: 1520742 (Python Code)

Max Activating Token Index: 294

Text #7

Max Range: 0.6587. Min Range: -0.6587

Max Act: 0.6402. Min Act: -0.0001

Data Index: 1418866 (Python Code)

Max Activating Token Index: 193

Text #8

Max Range: 0.6587. Min Range: -0.6587

Max Act: 0.5259. Min Act: -0.0001

Data Index: 1548061 (Python Code)

Max Activating Token Index: 927

Text #9

Max Range: 0.6587. Min Range: -0.6587

Max Act: 0.5804. Min Act: -0.0001

Data Index: 1406299 (Python Code)

Max Activating Token Index: 500

Text #10

Max Range: 0.6587. Min Range: -0.6587

Max Act: 0.5846. Min Act: -0.0001

Data Index: 1653979 (Python Code)

Max Activating Token Index: 676

Text #11

Max Range: 0.6587. Min Range: -0.6587

Max Act: 0.5553. Min Act: -0.0001

Data Index: 967143 (C4 (Web Text))

Max Activating Token Index: 941

Text #12

Max Range: 0.6587. Min Range: -0.6587

Max Act: 0.6587. Min Act: -0.0001

Data Index: 1636382 (Python Code)

Max Activating Token Index: 610

Text #13

Max Range: 0.6587. Min Range: -0.6587

Max Act: 0.5133. Min Act: -0.0001

Data Index: 1460275 (Python Code)

Max Activating Token Index: 277

Text #14

Max Range: 0.6587. Min Range: -0.6587

Max Act: 0.4869. Min Act: -0.0001

Data Index: 1598427 (Python Code)

Max Activating Token Index: 834

Text #15

Max Range: 0.6587. Min Range: -0.6587

Max Act: 0.4834. Min Act: -0.0001

Data Index: 261510 (C4 (Web Text))

Max Activating Token Index: 519

Text #16

Max Range: 0.6587. Min Range: -0.6587

Max Act: 0.5084. Min Act: -0.0001

Data Index: 1609485 (Python Code)

Max Activating Token Index: 71

Text #17

Max Range: 0.6587. Min Range: -0.6587

Max Act: 0.4546. Min Act: -0.0001

Data Index: 529903 (C4 (Web Text))

Max Activating Token Index: 638

Text #18

Max Range: 0.6587. Min Range: -0.6587

Max Act: 0.4364. Min Act: -0.0001

Data Index: 472686 (C4 (Web Text))

Max Activating Token Index: 909

Text #19

Max Range: 0.6587. Min Range: -0.6587

Max Act: 0.4260. Min Act: -0.0001

Data Index: 569246 (C4 (Web Text))

Max Activating Token Index: 403