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

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

Neuron 3833 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: 0.7435. Min Range: -0.7435

Max Act: 0.7435. Min Act: -0.0000

Data Index: 1307542 (C4 (Web Text))

Max Activating Token Index: 457

Text #1

Max Range: 0.7435. Min Range: -0.7435

Max Act: 0.6965. Min Act: -0.0000

Data Index: 890551 (C4 (Web Text))

Max Activating Token Index: 39

Text #2

Max Range: 0.7435. Min Range: -0.7435

Max Act: 0.6429. Min Act: -0.0000

Data Index: 443069 (C4 (Web Text))

Max Activating Token Index: 705

Text #3

Max Range: 0.7435. Min Range: -0.7435

Max Act: 0.5975. Min Act: -0.0000

Data Index: 1121670 (C4 (Web Text))

Max Activating Token Index: 659

Text #4

Max Range: 0.7435. Min Range: -0.7435

Max Act: 0.6756. Min Act: -0.0000

Data Index: 980034 (C4 (Web Text))

Max Activating Token Index: 469

Text #5

Max Range: 0.7435. Min Range: -0.7435

Max Act: 0.6218. Min Act: -0.0000

Data Index: 1338842 (C4 (Web Text))

Max Activating Token Index: 994

Text #6

Max Range: 0.7435. Min Range: -0.7435

Max Act: 0.6309. Min Act: -0.0000

Data Index: 194847 (C4 (Web Text))

Max Activating Token Index: 888

Text #7

Max Range: 0.7435. Min Range: -0.7435

Max Act: 0.6084. Min Act: -0.0000

Data Index: 372905 (C4 (Web Text))

Max Activating Token Index: 485

Text #8

Max Range: 0.7435. Min Range: -0.7435

Max Act: 0.5385. Min Act: -0.0000

Data Index: 525633 (C4 (Web Text))

Max Activating Token Index: 49

Text #9

Max Range: 0.7435. Min Range: -0.7435

Max Act: 0.4985. Min Act: -0.0000

Data Index: 341220 (C4 (Web Text))

Max Activating Token Index: 130

Text #10

Max Range: 0.7435. Min Range: -0.7435

Max Act: 0.5329. Min Act: -0.0000

Data Index: 877851 (C4 (Web Text))

Max Activating Token Index: 136

Text #11

Max Range: 0.7435. Min Range: -0.7435

Max Act: 0.4388. Min Act: -0.0000

Data Index: 884419 (C4 (Web Text))

Max Activating Token Index: 907

Text #12

Max Range: 0.7435. Min Range: -0.7435

Max Act: 0.5096. Min Act: -0.0000

Data Index: 116200 (C4 (Web Text))

Max Activating Token Index: 905

Text #13

Max Range: 0.7435. Min Range: -0.7435

Max Act: 0.4707. Min Act: -0.0000

Data Index: 1086673 (C4 (Web Text))

Max Activating Token Index: 997

Text #14

Max Range: 0.7435. Min Range: -0.7435

Max Act: 0.4570. Min Act: -0.0000

Data Index: 658647 (C4 (Web Text))

Max Activating Token Index: 196

Text #15

Max Range: 0.7435. Min Range: -0.7435

Max Act: 0.4697. Min Act: -0.0000

Data Index: 943120 (C4 (Web Text))

Max Activating Token Index: 50

Text #16

Max Range: 0.7435. Min Range: -0.7435

Max Act: 0.3633. Min Act: -0.0000

Data Index: 1425226 (Python Code)

Max Activating Token Index: 394

Text #17

Max Range: 0.7435. Min Range: -0.7435

Max Act: 0.4374. Min Act: -0.0000

Data Index: 1393722 (Python Code)

Max Activating Token Index: 272

Text #18

Max Range: 0.7435. Min Range: -0.7435

Max Act: 0.4493. Min Act: -0.0000

Data Index: 989027 (C4 (Web Text))

Max Activating Token Index: 89

Text #19

Max Range: 0.7435. Min Range: -0.7435

Max Act: 0.3709. Min Act: -0.0000

Data Index: 659145 (C4 (Web Text))

Max Activating Token Index: 259