Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4021 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.5632. Min Range: -0.5632

Max Act: 0.5632. Min Act: -0.0002

Data Index: 1509509 (Python Code)

Max Activating Token Index: 8

Text #1

Max Range: 0.5632. Min Range: -0.5632

Max Act: 0.5227. Min Act: -0.0002

Data Index: 1437833 (Python Code)

Max Activating Token Index: 8

Text #2

Max Range: 0.5632. Min Range: -0.5632

Max Act: 0.5248. Min Act: -0.0002

Data Index: 1561053 (Python Code)

Max Activating Token Index: 2

Text #3

Max Range: 0.5632. Min Range: -0.5632

Max Act: 0.5038. Min Act: -0.0002

Data Index: 1546600 (Python Code)

Max Activating Token Index: 8

Text #4

Max Range: 0.5632. Min Range: -0.5632

Max Act: 0.4950. Min Act: -0.0002

Data Index: 1491254 (Python Code)

Max Activating Token Index: 19

Text #5

Max Range: 0.5632. Min Range: -0.5632

Max Act: 0.4925. Min Act: -0.0002

Data Index: 1594901 (Python Code)

Max Activating Token Index: 5

Text #6

Max Range: 0.5632. Min Range: -0.5632

Max Act: 0.4655. Min Act: -0.0002

Data Index: 1426636 (Python Code)

Max Activating Token Index: 10

Text #7

Max Range: 0.5632. Min Range: -0.5632

Max Act: 0.4812. Min Act: -0.0002

Data Index: 1372470 (Python Code)

Max Activating Token Index: 231

Text #8

Max Range: 0.5632. Min Range: -0.5632

Max Act: 0.4449. Min Act: -0.0002

Data Index: 1572861 (Python Code)

Max Activating Token Index: 13

Text #9

Max Range: 0.5632. Min Range: -0.5632

Max Act: 0.4436. Min Act: -0.0002

Data Index: 1400624 (Python Code)

Max Activating Token Index: 10

Text #10

Max Range: 0.5632. Min Range: -0.5632

Max Act: 0.4350. Min Act: -0.0002

Data Index: 1447996 (Python Code)

Max Activating Token Index: 7

Text #11

Max Range: 0.5632. Min Range: -0.5632

Max Act: 0.4350. Min Act: -0.0003

Data Index: 1571051 (Python Code)

Max Activating Token Index: 7

Text #12

Max Range: 0.5632. Min Range: -0.5632

Max Act: 0.4179. Min Act: -0.0002

Data Index: 1442794 (Python Code)

Max Activating Token Index: 11

Text #13

Max Range: 0.5632. Min Range: -0.5632

Max Act: 0.4439. Min Act: -0.0003

Data Index: 1476410 (Python Code)

Max Activating Token Index: 8

Text #14

Max Range: 0.5632. Min Range: -0.5632

Max Act: 0.4427. Min Act: -0.0002

Data Index: 1367089 (Python Code)

Max Activating Token Index: 2

Text #15

Max Range: 0.5632. Min Range: -0.5632

Max Act: 0.4402. Min Act: -0.0003

Data Index: 1389380 (Python Code)

Max Activating Token Index: 10

Text #16

Max Range: 0.5632. Min Range: -0.5632

Max Act: 0.4240. Min Act: -0.0002

Data Index: 1547183 (Python Code)

Max Activating Token Index: 11

Text #17

Max Range: 0.5632. Min Range: -0.5632

Max Act: 0.4203. Min Act: -0.0002

Data Index: 1405996 (Python Code)

Max Activating Token Index: 2

Text #18

Max Range: 0.5632. Min Range: -0.5632

Max Act: 0.4321. Min Act: -0.0003

Data Index: 1395464 (Python Code)

Max Activating Token Index: 4

Text #19

Max Range: 0.5632. Min Range: -0.5632

Max Act: 0.4307. Min Act: -0.0002

Data Index: 1608300 (Python Code)

Max Activating Token Index: 2