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

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

Neuron 85 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.3625. Min Range: -7.3625

Max Act: 7.3625. Min Act: -0.0000

Data Index: 1502574 (Python Code)

Max Activating Token Index: 785

Text #1

Max Range: 7.3625. Min Range: -7.3625

Max Act: 6.8097. Min Act: -0.0000

Data Index: 1439944 (Python Code)

Max Activating Token Index: 539

Text #2

Max Range: 7.3625. Min Range: -7.3625

Max Act: 6.4637. Min Act: -0.0000

Data Index: 1490705 (Python Code)

Max Activating Token Index: 975

Text #3

Max Range: 7.3625. Min Range: -7.3625

Max Act: 6.0488. Min Act: -0.0000

Data Index: 1416557 (Python Code)

Max Activating Token Index: 382

Text #4

Max Range: 7.3625. Min Range: -7.3625

Max Act: 6.6506. Min Act: -0.0000

Data Index: 1639560 (Python Code)

Max Activating Token Index: 762

Text #5

Max Range: 7.3625. Min Range: -7.3625

Max Act: 6.4530. Min Act: -0.0000

Data Index: 1640276 (Python Code)

Max Activating Token Index: 803

Text #6

Max Range: 7.3625. Min Range: -7.3625

Max Act: 6.0138. Min Act: -0.0000

Data Index: 1515926 (Python Code)

Max Activating Token Index: 260

Text #7

Max Range: 7.3625. Min Range: -7.3625

Max Act: 6.2141. Min Act: -0.0000

Data Index: 1538423 (Python Code)

Max Activating Token Index: 924

Text #8

Max Range: 7.3625. Min Range: -7.3625

Max Act: 6.3761. Min Act: -0.0000

Data Index: 1568922 (Python Code)

Max Activating Token Index: 548

Text #9

Max Range: 7.3625. Min Range: -7.3625

Max Act: 6.3338. Min Act: -0.0000

Data Index: 1454898 (Python Code)

Max Activating Token Index: 397

Text #10

Max Range: 7.3625. Min Range: -7.3625

Max Act: 6.5119. Min Act: -0.0000

Data Index: 1635025 (Python Code)

Max Activating Token Index: 634

Text #11

Max Range: 7.3625. Min Range: -7.3625

Max Act: 6.4088. Min Act: -0.0000

Data Index: 1503593 (Python Code)

Max Activating Token Index: 175

Text #12

Max Range: 7.3625. Min Range: -7.3625

Max Act: 6.1993. Min Act: -0.0000

Data Index: 1419654 (Python Code)

Max Activating Token Index: 590

Text #13

Max Range: 7.3625. Min Range: -7.3625

Max Act: 6.1490. Min Act: -0.0000

Data Index: 1550379 (Python Code)

Max Activating Token Index: 648

Text #14

Max Range: 7.3625. Min Range: -7.3625

Max Act: 6.1226. Min Act: -0.0000

Data Index: 1432029 (Python Code)

Max Activating Token Index: 479

Text #15

Max Range: 7.3625. Min Range: -7.3625

Max Act: 6.0848. Min Act: -0.0000

Data Index: 1368307 (Python Code)

Max Activating Token Index: 739

Text #16

Max Range: 7.3625. Min Range: -7.3625

Max Act: 5.7219. Min Act: -0.0000

Data Index: 1488371 (Python Code)

Max Activating Token Index: 893

Text #17

Max Range: 7.3625. Min Range: -7.3625

Max Act: 5.9202. Min Act: -0.0000

Data Index: 1413998 (Python Code)

Max Activating Token Index: 919

Text #18

Max Range: 7.3625. Min Range: -7.3625

Max Act: 5.8824. Min Act: -0.0000

Data Index: 1427767 (Python Code)

Max Activating Token Index: 133

Text #19

Max Range: 7.3625. Min Range: -7.3625

Max Act: 5.8693. Min Act: -0.0000

Data Index: 1526809 (Python Code)

Max Activating Token Index: 576