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

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

Neuron 6131 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3735. Min Range: -1.3735

Max Act: 1.3735. Min Act: -0.0000

Data Index: 564866 (C4 (Web Text))

Max Activating Token Index: 814

Text #1

Max Range: 1.3735. Min Range: -1.3735

Max Act: 1.1591. Min Act: -0.0000

Data Index: 233210 (C4 (Web Text))

Max Activating Token Index: 443

Text #2

Max Range: 1.3735. Min Range: -1.3735

Max Act: 0.9508. Min Act: -0.0000

Data Index: 1139532 (C4 (Web Text))

Max Activating Token Index: 860

Text #3

Max Range: 1.3735. Min Range: -1.3735

Max Act: 0.8262. Min Act: -0.0000

Data Index: 262911 (C4 (Web Text))

Max Activating Token Index: 916

Text #4

Max Range: 1.3735. Min Range: -1.3735

Max Act: 0.9462. Min Act: -0.0000

Data Index: 81247 (C4 (Web Text))

Max Activating Token Index: 340

Text #5

Max Range: 1.3735. Min Range: -1.3735

Max Act: 0.8605. Min Act: -0.0000

Data Index: 297240 (C4 (Web Text))

Max Activating Token Index: 300

Text #6

Max Range: 1.3735. Min Range: -1.3735

Max Act: 0.7821. Min Act: -0.0000

Data Index: 1610438 (Python Code)

Max Activating Token Index: 719

Text #7

Max Range: 1.3735. Min Range: -1.3735

Max Act: 0.7623. Min Act: -0.0000

Data Index: 677642 (C4 (Web Text))

Max Activating Token Index: 576

Text #8

Max Range: 1.3735. Min Range: -1.3735

Max Act: 0.7220. Min Act: -0.0000

Data Index: 1536485 (Python Code)

Max Activating Token Index: 949

Text #9

Max Range: 1.3735. Min Range: -1.3735

Max Act: 0.6764. Min Act: -0.0000

Data Index: 1360392 (Python Code)

Max Activating Token Index: 193

Text #10

Max Range: 1.3735. Min Range: -1.3735

Max Act: 0.6458. Min Act: -0.0000

Data Index: 1304946 (C4 (Web Text))

Max Activating Token Index: 686

Text #11

Max Range: 1.3735. Min Range: -1.3735

Max Act: 0.6147. Min Act: -0.0000

Data Index: 1328148 (C4 (Web Text))

Max Activating Token Index: 997

Text #12

Max Range: 1.3735. Min Range: -1.3735

Max Act: 0.6745. Min Act: -0.0000

Data Index: 1628937 (Python Code)

Max Activating Token Index: 906

Text #13

Max Range: 1.3735. Min Range: -1.3735

Max Act: 0.6074. Min Act: -0.0000

Data Index: 575741 (C4 (Web Text))

Max Activating Token Index: 651

Text #14

Max Range: 1.3735. Min Range: -1.3735

Max Act: 0.6346. Min Act: -0.0000

Data Index: 1007251 (C4 (Web Text))

Max Activating Token Index: 664

Text #15

Max Range: 1.3735. Min Range: -1.3735

Max Act: 0.6044. Min Act: -0.0000

Data Index: 1634396 (Python Code)

Max Activating Token Index: 391

Text #16

Max Range: 1.3735. Min Range: -1.3735

Max Act: 0.6196. Min Act: -0.0000

Data Index: 366682 (C4 (Web Text))

Max Activating Token Index: 710

Text #17

Max Range: 1.3735. Min Range: -1.3735

Max Act: 0.6558. Min Act: -0.0000

Data Index: 1419074 (Python Code)

Max Activating Token Index: 832

Text #18

Max Range: 1.3735. Min Range: -1.3735

Max Act: 0.6028. Min Act: -0.0000

Data Index: 566297 (C4 (Web Text))

Max Activating Token Index: 384

Text #19

Max Range: 1.3735. Min Range: -1.3735

Max Act: 0.5338. Min Act: -0.0000

Data Index: 887388 (C4 (Web Text))

Max Activating Token Index: 356