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

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

Neuron 4609 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5254. Min Range: -0.5254

Max Act: 0.5254. Min Act: -0.0000

Data Index: 1557093 (Python Code)

Max Activating Token Index: 138

Text #1

Max Range: 0.5254. Min Range: -0.5254

Max Act: 0.5060. Min Act: -0.0000

Data Index: 1441096 (Python Code)

Max Activating Token Index: 775

Text #2

Max Range: 0.5254. Min Range: -0.5254

Max Act: 0.4667. Min Act: -0.0000

Data Index: 1484562 (Python Code)

Max Activating Token Index: 148

Text #3

Max Range: 0.5254. Min Range: -0.5254

Max Act: 0.4787. Min Act: -0.0000

Data Index: 1653964 (Python Code)

Max Activating Token Index: 942

Text #4

Max Range: 0.5254. Min Range: -0.5254

Max Act: 0.4437. Min Act: -0.0000

Data Index: 1580689 (Python Code)

Max Activating Token Index: 781

Text #5

Max Range: 0.5254. Min Range: -0.5254

Max Act: 0.4032. Min Act: -0.0000

Data Index: 1645555 (Python Code)

Max Activating Token Index: 438

Text #6

Max Range: 0.5254. Min Range: -0.5254

Max Act: 0.4220. Min Act: -0.0000

Data Index: 564331 (C4 (Web Text))

Max Activating Token Index: 373

Text #7

Max Range: 0.5254. Min Range: -0.5254

Max Act: 0.3935. Min Act: -0.0000

Data Index: 1462553 (Python Code)

Max Activating Token Index: 473

Text #8

Max Range: 0.5254. Min Range: -0.5254

Max Act: 0.3988. Min Act: -0.0000

Data Index: 1508660 (Python Code)

Max Activating Token Index: 428

Text #9

Max Range: 0.5254. Min Range: -0.5254

Max Act: 0.3972. Min Act: -0.0000

Data Index: 1452589 (Python Code)

Max Activating Token Index: 519

Text #10

Max Range: 0.5254. Min Range: -0.5254

Max Act: 0.4055. Min Act: -0.0000

Data Index: 1649729 (Python Code)

Max Activating Token Index: 292

Text #11

Max Range: 0.5254. Min Range: -0.5254

Max Act: 0.3875. Min Act: -0.0000

Data Index: 1560731 (Python Code)

Max Activating Token Index: 520

Text #12

Max Range: 0.5254. Min Range: -0.5254

Max Act: 0.3789. Min Act: -0.0000

Data Index: 1555365 (Python Code)

Max Activating Token Index: 407

Text #13

Max Range: 0.5254. Min Range: -0.5254

Max Act: 0.3707. Min Act: -0.0001

Data Index: 1371264 (Python Code)

Max Activating Token Index: 977

Text #14

Max Range: 0.5254. Min Range: -0.5254

Max Act: 0.3686. Min Act: -0.0001

Data Index: 1455613 (Python Code)

Max Activating Token Index: 915

Text #15

Max Range: 0.5254. Min Range: -0.5254

Max Act: 0.3654. Min Act: -0.0000

Data Index: 1177068 (C4 (Web Text))

Max Activating Token Index: 23

Text #16

Max Range: 0.5254. Min Range: -0.5254

Max Act: 0.3911. Min Act: -0.0000

Data Index: 1526685 (Python Code)

Max Activating Token Index: 295

Text #17

Max Range: 0.5254. Min Range: -0.5254

Max Act: 0.3556. Min Act: -0.0000

Data Index: 1631227 (Python Code)

Max Activating Token Index: 653

Text #18

Max Range: 0.5254. Min Range: -0.5254

Max Act: 0.3398. Min Act: -0.0000

Data Index: 1512776 (Python Code)

Max Activating Token Index: 678

Text #19

Max Range: 0.5254. Min Range: -0.5254

Max Act: 0.3498. Min Act: -0.0000

Data Index: 718040 (C4 (Web Text))

Max Activating Token Index: 930