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

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

Neuron 4584 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0284. Min Act: -0.0001

Data Index: 1457001 (Python Code)

Max Activating Token Index: 107

Text #1

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0287. Min Act: -0.0001

Data Index: 1584321 (Python Code)

Max Activating Token Index: 636

Text #2

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0283. Min Act: -0.0001

Data Index: 1553036 (Python Code)

Max Activating Token Index: 45

Text #3

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0283. Min Act: -0.0001

Data Index: 1620634 (Python Code)

Max Activating Token Index: 32

Text #4

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0286. Min Act: -0.0002

Data Index: 1495405 (Python Code)

Max Activating Token Index: 45

Text #5

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0285. Min Act: -0.0001

Data Index: 1392617 (Python Code)

Max Activating Token Index: 45

Text #6

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0286. Min Act: -0.0001

Data Index: 1392494 (Python Code)

Max Activating Token Index: 91

Text #7

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0281. Min Act: -0.0001

Data Index: 1613306 (Python Code)

Max Activating Token Index: 57

Text #8

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0280. Min Act: -0.0001

Data Index: 1380357 (Python Code)

Max Activating Token Index: 51

Text #9

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0281. Min Act: -0.0002

Data Index: 1584363 (Python Code)

Max Activating Token Index: 142

Text #10

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0281. Min Act: -0.0001

Data Index: 1534047 (Python Code)

Max Activating Token Index: 66

Text #11

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0281. Min Act: -0.0001

Data Index: 1549421 (Python Code)

Max Activating Token Index: 66

Text #12

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0279. Min Act: -0.0001

Data Index: 1624077 (Python Code)

Max Activating Token Index: 21

Text #13

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0276. Min Act: -0.0001

Data Index: 1397330 (Python Code)

Max Activating Token Index: 23

Text #14

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0281. Min Act: -0.0001

Data Index: 1409746 (Python Code)

Max Activating Token Index: 61

Text #15

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0277. Min Act: -0.0001

Data Index: 1452954 (Python Code)

Max Activating Token Index: 81

Text #16

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0277. Min Act: -0.0001

Data Index: 1619913 (Python Code)

Max Activating Token Index: 612

Text #17

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0278. Min Act: -0.0001

Data Index: 1426776 (Python Code)

Max Activating Token Index: 39

Text #18

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0281. Min Act: -0.0001

Data Index: 1547354 (Python Code)

Max Activating Token Index: 57

Text #19

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0277. Min Act: -0.0001

Data Index: 1590972 (Python Code)

Max Activating Token Index: 47