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

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

Neuron 3851 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6460. Min Range: -3.6460

Max Act: 3.6460. Min Act: -0.0000

Data Index: 1549524 (Python Code)

Max Activating Token Index: 9

Text #1

Max Range: 3.6460. Min Range: -3.6460

Max Act: 3.3305. Min Act: -0.0000

Data Index: 1520143 (Python Code)

Max Activating Token Index: 10

Text #2

Max Range: 3.6460. Min Range: -3.6460

Max Act: 3.3305. Min Act: -0.0000

Data Index: 1373923 (Python Code)

Max Activating Token Index: 10

Text #3

Max Range: 3.6460. Min Range: -3.6460

Max Act: 3.0035. Min Act: -0.0000

Data Index: 1562492 (Python Code)

Max Activating Token Index: 7

Text #4

Max Range: 3.6460. Min Range: -3.6460

Max Act: 2.9713. Min Act: -0.0000

Data Index: 1429546 (Python Code)

Max Activating Token Index: 20

Text #5

Max Range: 3.6460. Min Range: -3.6460

Max Act: 2.8063. Min Act: -0.0000

Data Index: 1508394 (Python Code)

Max Activating Token Index: 78

Text #6

Max Range: 3.6460. Min Range: -3.6460

Max Act: 2.8523. Min Act: -0.0000

Data Index: 1406636 (Python Code)

Max Activating Token Index: 5

Text #7

Max Range: 3.6460. Min Range: -3.6460

Max Act: 2.8523. Min Act: -0.0000

Data Index: 1587794 (Python Code)

Max Activating Token Index: 5

Text #8

Max Range: 3.6460. Min Range: -3.6460

Max Act: 2.8523. Min Act: -0.0000

Data Index: 1559832 (Python Code)

Max Activating Token Index: 5

Text #9

Max Range: 3.6460. Min Range: -3.6460

Max Act: 3.1324. Min Act: -0.0000

Data Index: 1491664 (Python Code)

Max Activating Token Index: 4

Text #10

Max Range: 3.6460. Min Range: -3.6460

Max Act: 3.1324. Min Act: -0.0000

Data Index: 1432520 (Python Code)

Max Activating Token Index: 4

Text #11

Max Range: 3.6460. Min Range: -3.6460

Max Act: 2.6130. Min Act: -0.0000

Data Index: 1567040 (Python Code)

Max Activating Token Index: 13

Text #12

Max Range: 3.6460. Min Range: -3.6460

Max Act: 2.3206. Min Act: -0.0000

Data Index: 1574411 (Python Code)

Max Activating Token Index: 194

Text #13

Max Range: 3.6460. Min Range: -3.6460

Max Act: 2.4280. Min Act: -0.0000

Data Index: 1394764 (Python Code)

Max Activating Token Index: 1010

Text #14

Max Range: 3.6460. Min Range: -3.6460

Max Act: 2.4162. Min Act: -0.0000

Data Index: 1613011 (Python Code)

Max Activating Token Index: 3

Text #15

Max Range: 3.6460. Min Range: -3.6460

Max Act: 2.4162. Min Act: -0.0000

Data Index: 1383805 (Python Code)

Max Activating Token Index: 3

Text #16

Max Range: 3.6460. Min Range: -3.6460

Max Act: 2.4162. Min Act: -0.0000

Data Index: 1550233 (Python Code)

Max Activating Token Index: 3

Text #17

Max Range: 3.6460. Min Range: -3.6460

Max Act: 2.4162. Min Act: -0.0000

Data Index: 1587662 (Python Code)

Max Activating Token Index: 3

Text #18

Max Range: 3.6460. Min Range: -3.6460

Max Act: 2.3554. Min Act: -0.0000

Data Index: 1538665 (Python Code)

Max Activating Token Index: 33

Text #19

Max Range: 3.6460. Min Range: -3.6460

Max Act: 2.3416. Min Act: -0.0000

Data Index: 1544201 (Python Code)

Max Activating Token Index: 31