Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2625 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0367. Min Act: -0.0004

Data Index: 1029981 (C4 (Web Text))

Max Activating Token Index: 5

Text #1

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0327. Min Act: -0.0004

Data Index: 1398824 (Python Code)

Max Activating Token Index: 7

Text #2

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0317. Min Act: -0.0004

Data Index: 1643366 (Python Code)

Max Activating Token Index: 6

Text #3

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0317. Min Act: -0.0004

Data Index: 1437970 (Python Code)

Max Activating Token Index: 6

Text #4

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0317. Min Act: -0.0004

Data Index: 1521718 (Python Code)

Max Activating Token Index: 6

Text #5

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0301. Min Act: -0.0004

Data Index: 1527271 (Python Code)

Max Activating Token Index: 5

Text #6

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0301. Min Act: -0.0004

Data Index: 1423322 (Python Code)

Max Activating Token Index: 5

Text #7

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0301. Min Act: -0.0004

Data Index: 1396645 (Python Code)

Max Activating Token Index: 5

Text #8

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0301. Min Act: -0.0004

Data Index: 1536732 (Python Code)

Max Activating Token Index: 5

Text #9

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0301. Min Act: -0.0004

Data Index: 1481788 (Python Code)

Max Activating Token Index: 5

Text #10

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0301. Min Act: -0.0004

Data Index: 1568991 (Python Code)

Max Activating Token Index: 5

Text #11

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0301. Min Act: -0.0004

Data Index: 1584487 (Python Code)

Max Activating Token Index: 5

Text #12

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0301. Min Act: -0.0004

Data Index: 1374799 (Python Code)

Max Activating Token Index: 5

Text #13

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0305. Min Act: -0.0004

Data Index: 1619603 (Python Code)

Max Activating Token Index: 8

Text #14

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0292. Min Act: -0.0004

Data Index: 1085692 (C4 (Web Text))

Max Activating Token Index: 900

Text #15

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0275. Min Act: -0.0004

Data Index: 554642 (C4 (Web Text))

Max Activating Token Index: 354

Text #16

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0282. Min Act: -0.0004

Data Index: 1471150 (Python Code)

Max Activating Token Index: 500

Text #17

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0279. Min Act: -0.0004

Data Index: 1498510 (Python Code)

Max Activating Token Index: 4

Text #18

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0279. Min Act: -0.0004

Data Index: 1438979 (Python Code)

Max Activating Token Index: 4

Text #19

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0279. Min Act: -0.0004

Data Index: 1415567 (Python Code)

Max Activating Token Index: 4