Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1770 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.5189. Min Range: -1.5189

Max Act: 1.5189. Min Act: -0.0000

Data Index: 1489132 (Python Code)

Max Activating Token Index: 323

Text #1

Max Range: 1.5189. Min Range: -1.5189

Max Act: 1.0990. Min Act: -0.0000

Data Index: 1494236 (Python Code)

Max Activating Token Index: 299

Text #2

Max Range: 1.5189. Min Range: -1.5189

Max Act: 1.1864. Min Act: -0.0001

Data Index: 1578166 (Python Code)

Max Activating Token Index: 291

Text #3

Max Range: 1.5189. Min Range: -1.5189

Max Act: 1.1462. Min Act: -0.0000

Data Index: 1586910 (Python Code)

Max Activating Token Index: 731

Text #4

Max Range: 1.5189. Min Range: -1.5189

Max Act: 0.9982. Min Act: -0.0001

Data Index: 1622109 (Python Code)

Max Activating Token Index: 874

Text #5

Max Range: 1.5189. Min Range: -1.5189

Max Act: 0.9327. Min Act: -0.0000

Data Index: 1575283 (Python Code)

Max Activating Token Index: 405

Text #6

Max Range: 1.5189. Min Range: -1.5189

Max Act: 0.9120. Min Act: -0.0001

Data Index: 1532302 (Python Code)

Max Activating Token Index: 533

Text #7

Max Range: 1.5189. Min Range: -1.5189

Max Act: 0.7923. Min Act: -0.0000

Data Index: 1365832 (Python Code)

Max Activating Token Index: 689

Text #8

Max Range: 1.5189. Min Range: -1.5189

Max Act: 0.8845. Min Act: -0.0001

Data Index: 1512412 (Python Code)

Max Activating Token Index: 581

Text #9

Max Range: 1.5189. Min Range: -1.5189

Max Act: 0.8967. Min Act: -0.0001

Data Index: 1483930 (Python Code)

Max Activating Token Index: 816

Text #10

Max Range: 1.5189. Min Range: -1.5189

Max Act: 0.8746. Min Act: -0.0000

Data Index: 1432945 (Python Code)

Max Activating Token Index: 282

Text #11

Max Range: 1.5189. Min Range: -1.5189

Max Act: 0.8913. Min Act: -0.0001

Data Index: 1402817 (Python Code)

Max Activating Token Index: 485

Text #12

Max Range: 1.5189. Min Range: -1.5189

Max Act: 0.8036. Min Act: 0.0000

Data Index: 1408340 (Python Code)

Max Activating Token Index: 283

Text #13

Max Range: 1.5189. Min Range: -1.5189

Max Act: 0.7573. Min Act: -0.0001

Data Index: 1547930 (Python Code)

Max Activating Token Index: 983

Text #14

Max Range: 1.5189. Min Range: -1.5189

Max Act: 0.8262. Min Act: -0.0001

Data Index: 1550031 (Python Code)

Max Activating Token Index: 819

Text #15

Max Range: 1.5189. Min Range: -1.5189

Max Act: 0.7716. Min Act: -0.0001

Data Index: 1427162 (Python Code)

Max Activating Token Index: 604

Text #16

Max Range: 1.5189. Min Range: -1.5189

Max Act: 0.7931. Min Act: -0.0000

Data Index: 1573920 (Python Code)

Max Activating Token Index: 1018

Text #17

Max Range: 1.5189. Min Range: -1.5189

Max Act: 0.7966. Min Act: -0.0000

Data Index: 1426180 (Python Code)

Max Activating Token Index: 371

Text #18

Max Range: 1.5189. Min Range: -1.5189

Max Act: 0.7573. Min Act: -0.0000

Data Index: 1437031 (Python Code)

Max Activating Token Index: 486

Text #19

Max Range: 1.5189. Min Range: -1.5189

Max Act: 0.8047. Min Act: -0.0001

Data Index: 1486164 (Python Code)

Max Activating Token Index: 462