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

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

Neuron 4115 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.3116. Min Range: -7.3116

Max Act: 7.3116. Min Act: -0.0000

Data Index: 245497 (C4 (Web Text))

Max Activating Token Index: 759

Text #1

Max Range: 7.3116. Min Range: -7.3116

Max Act: 4.4207. Min Act: -0.0000

Data Index: 294200 (C4 (Web Text))

Max Activating Token Index: 482

Text #2

Max Range: 7.3116. Min Range: -7.3116

Max Act: 4.2861. Min Act: -0.0000

Data Index: 141629 (C4 (Web Text))

Max Activating Token Index: 95

Text #3

Max Range: 7.3116. Min Range: -7.3116

Max Act: 4.6066. Min Act: -0.0000

Data Index: 1077359 (C4 (Web Text))

Max Activating Token Index: 546

Text #4

Max Range: 7.3116. Min Range: -7.3116

Max Act: 4.2338. Min Act: -0.0000

Data Index: 1242351 (C4 (Web Text))

Max Activating Token Index: 282

Text #5

Max Range: 7.3116. Min Range: -7.3116

Max Act: 4.3010. Min Act: -0.0000

Data Index: 17070 (C4 (Web Text))

Max Activating Token Index: 910

Text #6

Max Range: 7.3116. Min Range: -7.3116

Max Act: 4.0564. Min Act: -0.0000

Data Index: 149684 (C4 (Web Text))

Max Activating Token Index: 657

Text #7

Max Range: 7.3116. Min Range: -7.3116

Max Act: 4.1527. Min Act: -0.0000

Data Index: 1043089 (C4 (Web Text))

Max Activating Token Index: 619

Text #8

Max Range: 7.3116. Min Range: -7.3116

Max Act: 3.5724. Min Act: -0.0000

Data Index: 1149978 (C4 (Web Text))

Max Activating Token Index: 314

Text #9

Max Range: 7.3116. Min Range: -7.3116

Max Act: 4.0181. Min Act: -0.0000

Data Index: 717612 (C4 (Web Text))

Max Activating Token Index: 57

Text #10

Max Range: 7.3116. Min Range: -7.3116

Max Act: 3.6310. Min Act: -0.0000

Data Index: 12481 (C4 (Web Text))

Max Activating Token Index: 243

Text #11

Max Range: 7.3116. Min Range: -7.3116

Max Act: 3.5312. Min Act: -0.0000

Data Index: 109021 (C4 (Web Text))

Max Activating Token Index: 177

Text #12

Max Range: 7.3116. Min Range: -7.3116

Max Act: 3.6799. Min Act: -0.0000

Data Index: 343420 (C4 (Web Text))

Max Activating Token Index: 753

Text #13

Max Range: 7.3116. Min Range: -7.3116

Max Act: 3.6102. Min Act: -0.0000

Data Index: 546205 (C4 (Web Text))

Max Activating Token Index: 604

Text #14

Max Range: 7.3116. Min Range: -7.3116

Max Act: 3.6436. Min Act: -0.0000

Data Index: 133327 (C4 (Web Text))

Max Activating Token Index: 412

Text #15

Max Range: 7.3116. Min Range: -7.3116

Max Act: 3.4822. Min Act: -0.0000

Data Index: 697179 (C4 (Web Text))

Max Activating Token Index: 499

Text #16

Max Range: 7.3116. Min Range: -7.3116

Max Act: 3.1389. Min Act: -0.0000

Data Index: 727526 (C4 (Web Text))

Max Activating Token Index: 430

Text #17

Max Range: 7.3116. Min Range: -7.3116

Max Act: 3.3918. Min Act: -0.0000

Data Index: 279164 (C4 (Web Text))

Max Activating Token Index: 702

Text #18

Max Range: 7.3116. Min Range: -7.3116

Max Act: 3.2375. Min Act: -0.0000

Data Index: 678478 (C4 (Web Text))

Max Activating Token Index: 891

Text #19

Max Range: 7.3116. Min Range: -7.3116

Max Act: 3.3851. Min Act: -0.0000

Data Index: 313758 (C4 (Web Text))

Max Activating Token Index: 30