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

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

Neuron 500 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0502. Min Range: -3.0502

Max Act: 2.8419. Min Act: -0.0000

Data Index: 1410342 (Python Code)

Max Activating Token Index: 655

Text #1

Max Range: 3.0502. Min Range: -3.0502

Max Act: 2.8130. Min Act: -0.0000

Data Index: 1606846 (Python Code)

Max Activating Token Index: 818

Text #2

Max Range: 3.0502. Min Range: -3.0502

Max Act: 2.9212. Min Act: -0.0000

Data Index: 50482 (C4 (Web Text))

Max Activating Token Index: 26

Text #3

Max Range: 3.0502. Min Range: -3.0502

Max Act: 3.0502. Min Act: -0.0000

Data Index: 809866 (C4 (Web Text))

Max Activating Token Index: 296

Text #4

Max Range: 3.0502. Min Range: -3.0502

Max Act: 2.8707. Min Act: -0.0000

Data Index: 1397633 (Python Code)

Max Activating Token Index: 668

Text #5

Max Range: 3.0502. Min Range: -3.0502

Max Act: 2.8405. Min Act: -0.0000

Data Index: 1628820 (Python Code)

Max Activating Token Index: 738

Text #6

Max Range: 3.0502. Min Range: -3.0502

Max Act: 2.7014. Min Act: -0.0000

Data Index: 114194 (C4 (Web Text))

Max Activating Token Index: 58

Text #7

Max Range: 3.0502. Min Range: -3.0502

Max Act: 2.6784. Min Act: -0.0000

Data Index: 412613 (C4 (Web Text))

Max Activating Token Index: 635

Text #8

Max Range: 3.0502. Min Range: -3.0502

Max Act: 2.4968. Min Act: -0.0000

Data Index: 1206488 (C4 (Web Text))

Max Activating Token Index: 50

Text #9

Max Range: 3.0502. Min Range: -3.0502

Max Act: 2.6947. Min Act: -0.0000

Data Index: 1519326 (Python Code)

Max Activating Token Index: 904

Text #10

Max Range: 3.0502. Min Range: -3.0502

Max Act: 2.5898. Min Act: -0.0000

Data Index: 1410432 (Python Code)

Max Activating Token Index: 616

Text #11

Max Range: 3.0502. Min Range: -3.0502

Max Act: 2.5274. Min Act: -0.0000

Data Index: 1133434 (C4 (Web Text))

Max Activating Token Index: 99

Text #12

Max Range: 3.0502. Min Range: -3.0502

Max Act: 2.3944. Min Act: -0.0000

Data Index: 397866 (C4 (Web Text))

Max Activating Token Index: 99

Text #13

Max Range: 3.0502. Min Range: -3.0502

Max Act: 2.5093. Min Act: -0.0000

Data Index: 749836 (C4 (Web Text))

Max Activating Token Index: 67

Text #14

Max Range: 3.0502. Min Range: -3.0502

Max Act: 2.5189. Min Act: -0.0000

Data Index: 1287886 (C4 (Web Text))

Max Activating Token Index: 57

Text #15

Max Range: 3.0502. Min Range: -3.0502

Max Act: 2.3647. Min Act: -0.0000

Data Index: 1439625 (Python Code)

Max Activating Token Index: 835

Text #16

Max Range: 3.0502. Min Range: -3.0502

Max Act: 2.7096. Min Act: -0.0000

Data Index: 1415933 (Python Code)

Max Activating Token Index: 775

Text #17

Max Range: 3.0502. Min Range: -3.0502

Max Act: 2.4364. Min Act: -0.0000

Data Index: 1307739 (C4 (Web Text))

Max Activating Token Index: 62

Text #18

Max Range: 3.0502. Min Range: -3.0502

Max Act: 2.5409. Min Act: -0.0000

Data Index: 1487364 (Python Code)

Max Activating Token Index: 887

Text #19

Max Range: 3.0502. Min Range: -3.0502

Max Act: 2.3063. Min Act: -0.0000

Data Index: 213702 (C4 (Web Text))

Max Activating Token Index: 199