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

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

Neuron 3586 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8277. Min Range: -0.8277

Max Act: 0.8231. Min Act: -0.0000

Data Index: 1367009 (Python Code)

Max Activating Token Index: 845

Text #1

Max Range: 0.8277. Min Range: -0.8277

Max Act: 0.8277. Min Act: -0.0000

Data Index: 1636108 (Python Code)

Max Activating Token Index: 766

Text #2

Max Range: 0.8277. Min Range: -0.8277

Max Act: 0.7360. Min Act: -0.0000

Data Index: 1608250 (Python Code)

Max Activating Token Index: 964

Text #3

Max Range: 0.8277. Min Range: -0.8277

Max Act: 0.7124. Min Act: -0.0000

Data Index: 1562828 (Python Code)

Max Activating Token Index: 570

Text #4

Max Range: 0.8277. Min Range: -0.8277

Max Act: 0.7664. Min Act: -0.0000

Data Index: 1486196 (Python Code)

Max Activating Token Index: 253

Text #5

Max Range: 0.8277. Min Range: -0.8277

Max Act: 0.6662. Min Act: -0.0000

Data Index: 1462871 (Python Code)

Max Activating Token Index: 206

Text #6

Max Range: 0.8277. Min Range: -0.8277

Max Act: 0.6892. Min Act: -0.0000

Data Index: 1453928 (Python Code)

Max Activating Token Index: 419

Text #7

Max Range: 0.8277. Min Range: -0.8277

Max Act: 0.6566. Min Act: -0.0000

Data Index: 1493980 (Python Code)

Max Activating Token Index: 423

Text #8

Max Range: 0.8277. Min Range: -0.8277

Max Act: 0.6505. Min Act: -0.0000

Data Index: 1636431 (Python Code)

Max Activating Token Index: 242

Text #9

Max Range: 0.8277. Min Range: -0.8277

Max Act: 0.6903. Min Act: -0.0000

Data Index: 961715 (C4 (Web Text))

Max Activating Token Index: 762

Text #10

Max Range: 0.8277. Min Range: -0.8277

Max Act: 0.6970. Min Act: -0.0000

Data Index: 1636994 (Python Code)

Max Activating Token Index: 572

Text #11

Max Range: 0.8277. Min Range: -0.8277

Max Act: 0.6777. Min Act: -0.0000

Data Index: 1473000 (Python Code)

Max Activating Token Index: 789

Text #12

Max Range: 0.8277. Min Range: -0.8277

Max Act: 0.6542. Min Act: -0.0000

Data Index: 228038 (C4 (Web Text))

Max Activating Token Index: 681

Text #13

Max Range: 0.8277. Min Range: -0.8277

Max Act: 0.6298. Min Act: -0.0000

Data Index: 270618 (C4 (Web Text))

Max Activating Token Index: 689

Text #14

Max Range: 0.8277. Min Range: -0.8277

Max Act: 0.6528. Min Act: -0.0000

Data Index: 1484333 (Python Code)

Max Activating Token Index: 93

Text #15

Max Range: 0.8277. Min Range: -0.8277

Max Act: 0.6688. Min Act: -0.0000

Data Index: 1588921 (Python Code)

Max Activating Token Index: 218

Text #16

Max Range: 0.8277. Min Range: -0.8277

Max Act: 0.6143. Min Act: -0.0000

Data Index: 1288720 (C4 (Web Text))

Max Activating Token Index: 933

Text #17

Max Range: 0.8277. Min Range: -0.8277

Max Act: 0.6856. Min Act: -0.0000

Data Index: 1481650 (Python Code)

Max Activating Token Index: 448

Text #18

Max Range: 0.8277. Min Range: -0.8277

Max Act: 0.6489. Min Act: -0.0000

Data Index: 518005 (C4 (Web Text))

Max Activating Token Index: 724

Text #19

Max Range: 0.8277. Min Range: -0.8277

Max Act: 0.6297. Min Act: -0.0000

Data Index: 884534 (C4 (Web Text))

Max Activating Token Index: 12