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

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

Neuron 3818 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3926. Min Range: -1.3926

Max Act: 1.3926. Min Act: -0.0000

Data Index: 123938 (C4 (Web Text))

Max Activating Token Index: 768

Text #1

Max Range: 1.3926. Min Range: -1.3926

Max Act: 1.2452. Min Act: -0.0000

Data Index: 962750 (C4 (Web Text))

Max Activating Token Index: 763

Text #2

Max Range: 1.3926. Min Range: -1.3926

Max Act: 1.3086. Min Act: -0.0000

Data Index: 438747 (C4 (Web Text))

Max Activating Token Index: 436

Text #3

Max Range: 1.3926. Min Range: -1.3926

Max Act: 1.2583. Min Act: -0.0000

Data Index: 390656 (C4 (Web Text))

Max Activating Token Index: 808

Text #4

Max Range: 1.3926. Min Range: -1.3926

Max Act: 1.2663. Min Act: -0.0000

Data Index: 1127399 (C4 (Web Text))

Max Activating Token Index: 524

Text #5

Max Range: 1.3926. Min Range: -1.3926

Max Act: 1.1947. Min Act: -0.0000

Data Index: 303291 (C4 (Web Text))

Max Activating Token Index: 773

Text #6

Max Range: 1.3926. Min Range: -1.3926

Max Act: 1.1692. Min Act: -0.0000

Data Index: 1555412 (Python Code)

Max Activating Token Index: 625

Text #7

Max Range: 1.3926. Min Range: -1.3926

Max Act: 1.2037. Min Act: -0.0000

Data Index: 1139128 (C4 (Web Text))

Max Activating Token Index: 166

Text #8

Max Range: 1.3926. Min Range: -1.3926

Max Act: 1.1969. Min Act: -0.0000

Data Index: 912509 (C4 (Web Text))

Max Activating Token Index: 82

Text #9

Max Range: 1.3926. Min Range: -1.3926

Max Act: 1.1810. Min Act: -0.0000

Data Index: 1384031 (Python Code)

Max Activating Token Index: 514

Text #10

Max Range: 1.3926. Min Range: -1.3926

Max Act: 1.1977. Min Act: -0.0000

Data Index: 879859 (C4 (Web Text))

Max Activating Token Index: 1004

Text #11

Max Range: 1.3926. Min Range: -1.3926

Max Act: 1.1123. Min Act: -0.0000

Data Index: 961743 (C4 (Web Text))

Max Activating Token Index: 635

Text #12

Max Range: 1.3926. Min Range: -1.3926

Max Act: 1.0977. Min Act: -0.0000

Data Index: 1043595 (C4 (Web Text))

Max Activating Token Index: 289

Text #13

Max Range: 1.3926. Min Range: -1.3926

Max Act: 1.0289. Min Act: -0.0000

Data Index: 321317 (C4 (Web Text))

Max Activating Token Index: 460

Text #14

Max Range: 1.3926. Min Range: -1.3926

Max Act: 1.1260. Min Act: -0.0000

Data Index: 148176 (C4 (Web Text))

Max Activating Token Index: 901

Text #15

Max Range: 1.3926. Min Range: -1.3926

Max Act: 1.0249. Min Act: -0.0000

Data Index: 51526 (C4 (Web Text))

Max Activating Token Index: 204

Text #16

Max Range: 1.3926. Min Range: -1.3926

Max Act: 1.0642. Min Act: -0.0000

Data Index: 1411496 (Python Code)

Max Activating Token Index: 791

Text #17

Max Range: 1.3926. Min Range: -1.3926

Max Act: 1.1039. Min Act: -0.0000

Data Index: 346993 (C4 (Web Text))

Max Activating Token Index: 42

Text #18

Max Range: 1.3926. Min Range: -1.3926

Max Act: 1.0608. Min Act: -0.0000

Data Index: 1213267 (C4 (Web Text))

Max Activating Token Index: 12

Text #19

Max Range: 1.3926. Min Range: -1.3926

Max Act: 1.0518. Min Act: -0.0000

Data Index: 557625 (C4 (Web Text))

Max Activating Token Index: 450