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

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

Neuron 4197 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: 1.5686. Min Range: -1.5686

Max Act: 1.5686. Min Act: -0.0000

Data Index: 1348642 (C4 (Web Text))

Max Activating Token Index: 66

Text #1

Max Range: 1.5686. Min Range: -1.5686

Max Act: 1.4647. Min Act: -0.0000

Data Index: 340099 (C4 (Web Text))

Max Activating Token Index: 348

Text #2

Max Range: 1.5686. Min Range: -1.5686

Max Act: 1.4575. Min Act: -0.0000

Data Index: 9384 (C4 (Web Text))

Max Activating Token Index: 55

Text #3

Max Range: 1.5686. Min Range: -1.5686

Max Act: 1.3597. Min Act: -0.0000

Data Index: 720403 (C4 (Web Text))

Max Activating Token Index: 86

Text #4

Max Range: 1.5686. Min Range: -1.5686

Max Act: 1.2718. Min Act: -0.0000

Data Index: 432860 (C4 (Web Text))

Max Activating Token Index: 633

Text #5

Max Range: 1.5686. Min Range: -1.5686

Max Act: 1.2533. Min Act: -0.0000

Data Index: 1177408 (C4 (Web Text))

Max Activating Token Index: 261

Text #6

Max Range: 1.5686. Min Range: -1.5686

Max Act: 1.1918. Min Act: -0.0000

Data Index: 60871 (C4 (Web Text))

Max Activating Token Index: 381

Text #7

Max Range: 1.5686. Min Range: -1.5686

Max Act: 1.0257. Min Act: -0.0000

Data Index: 379394 (C4 (Web Text))

Max Activating Token Index: 811

Text #8

Max Range: 1.5686. Min Range: -1.5686

Max Act: 1.0143. Min Act: -0.0000

Data Index: 472476 (C4 (Web Text))

Max Activating Token Index: 806

Text #9

Max Range: 1.5686. Min Range: -1.5686

Max Act: 0.9940. Min Act: -0.0000

Data Index: 1185302 (C4 (Web Text))

Max Activating Token Index: 448

Text #10

Max Range: 1.5686. Min Range: -1.5686

Max Act: 0.9580. Min Act: -0.0000

Data Index: 1296356 (C4 (Web Text))

Max Activating Token Index: 430

Text #11

Max Range: 1.5686. Min Range: -1.5686

Max Act: 0.9817. Min Act: -0.0000

Data Index: 221448 (C4 (Web Text))

Max Activating Token Index: 467

Text #12

Max Range: 1.5686. Min Range: -1.5686

Max Act: 1.0219. Min Act: -0.0000

Data Index: 385315 (C4 (Web Text))

Max Activating Token Index: 786

Text #13

Max Range: 1.5686. Min Range: -1.5686

Max Act: 0.9800. Min Act: -0.0000

Data Index: 107118 (C4 (Web Text))

Max Activating Token Index: 871

Text #14

Max Range: 1.5686. Min Range: -1.5686

Max Act: 0.9357. Min Act: -0.0000

Data Index: 611706 (C4 (Web Text))

Max Activating Token Index: 177

Text #15

Max Range: 1.5686. Min Range: -1.5686

Max Act: 1.0430. Min Act: -0.0000

Data Index: 946371 (C4 (Web Text))

Max Activating Token Index: 905

Text #16

Max Range: 1.5686. Min Range: -1.5686

Max Act: 0.9158. Min Act: -0.0000

Data Index: 120214 (C4 (Web Text))

Max Activating Token Index: 701

Text #17

Max Range: 1.5686. Min Range: -1.5686

Max Act: 0.9633. Min Act: -0.0000

Data Index: 1381832 (Python Code)

Max Activating Token Index: 882

Text #18

Max Range: 1.5686. Min Range: -1.5686

Max Act: 0.9477. Min Act: -0.0000

Data Index: 227630 (C4 (Web Text))

Max Activating Token Index: 719

Text #19

Max Range: 1.5686. Min Range: -1.5686

Max Act: 0.9377. Min Act: -0.0000

Data Index: 854845 (C4 (Web Text))

Max Activating Token Index: 85