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

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

Neuron 5057 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0610. Min Act: -0.0001

Data Index: 685089 (C4 (Web Text))

Max Activating Token Index: 917

Text #1

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0508. Min Act: -0.0001

Data Index: 1080649 (C4 (Web Text))

Max Activating Token Index: 320

Text #2

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0476. Min Act: -0.0001

Data Index: 1387763 (Python Code)

Max Activating Token Index: 72

Text #3

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0419. Min Act: -0.0001

Data Index: 1467237 (Python Code)

Max Activating Token Index: 1023

Text #4

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0485. Min Act: -0.0001

Data Index: 1052764 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0419. Min Act: -0.0001

Data Index: 1001474 (C4 (Web Text))

Max Activating Token Index: 827

Text #6

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0435. Min Act: -0.0001

Data Index: 1577365 (Python Code)

Max Activating Token Index: 784

Text #7

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0419. Min Act: -0.0002

Data Index: 408791 (C4 (Web Text))

Max Activating Token Index: 944

Text #8

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0335. Min Act: -0.0001

Data Index: 733041 (C4 (Web Text))

Max Activating Token Index: 789

Text #9

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0428. Min Act: -0.0001

Data Index: 923019 (C4 (Web Text))

Max Activating Token Index: 735

Text #10

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0406. Min Act: -0.0001

Data Index: 730886 (C4 (Web Text))

Max Activating Token Index: 807

Text #11

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0412. Min Act: -0.0001

Data Index: 512000 (C4 (Web Text))

Max Activating Token Index: 885

Text #12

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0394. Min Act: -0.0001

Data Index: 253 (C4 (Web Text))

Max Activating Token Index: 219

Text #13

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0375. Min Act: -0.0001

Data Index: 1646855 (Python Code)

Max Activating Token Index: 917

Text #14

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0367. Min Act: -0.0001

Data Index: 1005199 (C4 (Web Text))

Max Activating Token Index: 904

Text #15

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0351. Min Act: -0.0001

Data Index: 1309047 (C4 (Web Text))

Max Activating Token Index: 309

Text #16

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0402. Min Act: -0.0001

Data Index: 512846 (C4 (Web Text))

Max Activating Token Index: 917

Text #17

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0398. Min Act: -0.0001

Data Index: 734138 (C4 (Web Text))

Max Activating Token Index: 19

Text #18

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0427. Min Act: -0.0001

Data Index: 1404235 (Python Code)

Max Activating Token Index: 68

Text #19

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0397. Min Act: -0.0001

Data Index: 1613867 (Python Code)

Max Activating Token Index: 5