Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1401 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.7696. Min Range: -0.7696

Max Act: 0.6570. Min Act: -0.0000

Data Index: 1653725 (Python Code)

Max Activating Token Index: 310

Text #1

Max Range: 0.7696. Min Range: -0.7696

Max Act: 0.5399. Min Act: -0.0000

Data Index: 1523218 (Python Code)

Max Activating Token Index: 150

Text #2

Max Range: 0.7696. Min Range: -0.7696

Max Act: 0.7105. Min Act: -0.0000

Data Index: 1326482 (C4 (Web Text))

Max Activating Token Index: 264

Text #3

Max Range: 0.7696. Min Range: -0.7696

Max Act: 0.6950. Min Act: -0.0000

Data Index: 1478947 (Python Code)

Max Activating Token Index: 886

Text #4

Max Range: 0.7696. Min Range: -0.7696

Max Act: 0.5103. Min Act: -0.0000

Data Index: 1391838 (Python Code)

Max Activating Token Index: 554

Text #5

Max Range: 0.7696. Min Range: -0.7696

Max Act: 0.6896. Min Act: -0.0000

Data Index: 1481827 (Python Code)

Max Activating Token Index: 399

Text #6

Max Range: 0.7696. Min Range: -0.7696

Max Act: 0.6663. Min Act: -0.0000

Data Index: 1599025 (Python Code)

Max Activating Token Index: 695

Text #7

Max Range: 0.7696. Min Range: -0.7696

Max Act: 0.5857. Min Act: -0.0000

Data Index: 1449075 (Python Code)

Max Activating Token Index: 703

Text #8

Max Range: 0.7696. Min Range: -0.7696

Max Act: 0.5419. Min Act: -0.0000

Data Index: 1532849 (Python Code)

Max Activating Token Index: 129

Text #9

Max Range: 0.7696. Min Range: -0.7696

Max Act: 0.6808. Min Act: -0.0000

Data Index: 1499050 (Python Code)

Max Activating Token Index: 308

Text #10

Max Range: 0.7696. Min Range: -0.7696

Max Act: 0.4344. Min Act: -0.0000

Data Index: 1563853 (Python Code)

Max Activating Token Index: 695

Text #11

Max Range: 0.7696. Min Range: -0.7696

Max Act: 0.6255. Min Act: -0.0000

Data Index: 1441029 (Python Code)

Max Activating Token Index: 686

Text #12

Max Range: 0.7696. Min Range: -0.7696

Max Act: 0.5095. Min Act: -0.0000

Data Index: 1393961 (Python Code)

Max Activating Token Index: 46

Text #13

Max Range: 0.7696. Min Range: -0.7696

Max Act: 0.5235. Min Act: -0.0000

Data Index: 1511511 (Python Code)

Max Activating Token Index: 517

Text #14

Max Range: 0.7696. Min Range: -0.7696

Max Act: 0.7696. Min Act: -0.0000

Data Index: 1399400 (Python Code)

Max Activating Token Index: 650

Text #15

Max Range: 0.7696. Min Range: -0.7696

Max Act: 0.5701. Min Act: -0.0000

Data Index: 1516354 (Python Code)

Max Activating Token Index: 752

Text #16

Max Range: 0.7696. Min Range: -0.7696

Max Act: 0.6956. Min Act: -0.0000

Data Index: 1597411 (Python Code)

Max Activating Token Index: 642

Text #17

Max Range: 0.7696. Min Range: -0.7696

Max Act: 0.4824. Min Act: -0.0000

Data Index: 1560375 (Python Code)

Max Activating Token Index: 496

Text #18

Max Range: 0.7696. Min Range: -0.7696

Max Act: 0.5672. Min Act: -0.0000

Data Index: 1382419 (Python Code)

Max Activating Token Index: 174

Text #19

Max Range: 0.7696. Min Range: -0.7696

Max Act: 0.4790. Min Act: -0.0000

Data Index: 1280324 (C4 (Web Text))

Max Activating Token Index: 23