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

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

Neuron 5411 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5992. Min Range: -1.5992

Max Act: 1.5992. Min Act: -0.0000

Data Index: 197617 (C4 (Web Text))

Max Activating Token Index: 413

Text #1

Max Range: 1.5992. Min Range: -1.5992

Max Act: 1.4277. Min Act: -0.0000

Data Index: 871074 (C4 (Web Text))

Max Activating Token Index: 346

Text #2

Max Range: 1.5992. Min Range: -1.5992

Max Act: 1.4500. Min Act: -0.0000

Data Index: 520385 (C4 (Web Text))

Max Activating Token Index: 89

Text #3

Max Range: 1.5992. Min Range: -1.5992

Max Act: 1.4581. Min Act: -0.0000

Data Index: 760262 (C4 (Web Text))

Max Activating Token Index: 426

Text #4

Max Range: 1.5992. Min Range: -1.5992

Max Act: 1.3998. Min Act: -0.0000

Data Index: 491741 (C4 (Web Text))

Max Activating Token Index: 912

Text #5

Max Range: 1.5992. Min Range: -1.5992

Max Act: 1.3655. Min Act: -0.0000

Data Index: 932264 (C4 (Web Text))

Max Activating Token Index: 22

Text #6

Max Range: 1.5992. Min Range: -1.5992

Max Act: 1.3915. Min Act: -0.0000

Data Index: 735068 (C4 (Web Text))

Max Activating Token Index: 54

Text #7

Max Range: 1.5992. Min Range: -1.5992

Max Act: 1.3307. Min Act: -0.0000

Data Index: 1146475 (C4 (Web Text))

Max Activating Token Index: 231

Text #8

Max Range: 1.5992. Min Range: -1.5992

Max Act: 1.2593. Min Act: -0.0000

Data Index: 378593 (C4 (Web Text))

Max Activating Token Index: 678

Text #9

Max Range: 1.5992. Min Range: -1.5992

Max Act: 1.2902. Min Act: -0.0000

Data Index: 780000 (C4 (Web Text))

Max Activating Token Index: 17

Text #10

Max Range: 1.5992. Min Range: -1.5992

Max Act: 1.2385. Min Act: -0.0000

Data Index: 865032 (C4 (Web Text))

Max Activating Token Index: 57

Text #11

Max Range: 1.5992. Min Range: -1.5992

Max Act: 1.2364. Min Act: -0.0000

Data Index: 499129 (C4 (Web Text))

Max Activating Token Index: 112

Text #12

Max Range: 1.5992. Min Range: -1.5992

Max Act: 1.2208. Min Act: -0.0000

Data Index: 407900 (C4 (Web Text))

Max Activating Token Index: 13

Text #13

Max Range: 1.5992. Min Range: -1.5992

Max Act: 1.1808. Min Act: -0.0000

Data Index: 595687 (C4 (Web Text))

Max Activating Token Index: 624

Text #14

Max Range: 1.5992. Min Range: -1.5992

Max Act: 1.1495. Min Act: -0.0000

Data Index: 799591 (C4 (Web Text))

Max Activating Token Index: 807

Text #15

Max Range: 1.5992. Min Range: -1.5992

Max Act: 1.2063. Min Act: -0.0000

Data Index: 16492 (C4 (Web Text))

Max Activating Token Index: 582

Text #16

Max Range: 1.5992. Min Range: -1.5992

Max Act: 1.2033. Min Act: -0.0000

Data Index: 130571 (C4 (Web Text))

Max Activating Token Index: 493

Text #17

Max Range: 1.5992. Min Range: -1.5992

Max Act: 1.1895. Min Act: -0.0000

Data Index: 93254 (C4 (Web Text))

Max Activating Token Index: 912

Text #18

Max Range: 1.5992. Min Range: -1.5992

Max Act: 1.1555. Min Act: -0.0000

Data Index: 696142 (C4 (Web Text))

Max Activating Token Index: 314

Text #19

Max Range: 1.5992. Min Range: -1.5992

Max Act: 1.1821. Min Act: -0.0000

Data Index: 350490 (C4 (Web Text))

Max Activating Token Index: 130