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

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

Neuron 3744 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0460. Min Range: -2.0460

Max Act: 2.0460. Min Act: -0.0000

Data Index: 1480984 (Python Code)

Max Activating Token Index: 179

Text #1

Max Range: 2.0460. Min Range: -2.0460

Max Act: 1.5726. Min Act: -0.0000

Data Index: 1586908 (Python Code)

Max Activating Token Index: 360

Text #2

Max Range: 2.0460. Min Range: -2.0460

Max Act: 1.6605. Min Act: -0.0000

Data Index: 1415893 (Python Code)

Max Activating Token Index: 356

Text #3

Max Range: 2.0460. Min Range: -2.0460

Max Act: 1.5714. Min Act: -0.0000

Data Index: 1550766 (Python Code)

Max Activating Token Index: 978

Text #4

Max Range: 2.0460. Min Range: -2.0460

Max Act: 1.6073. Min Act: -0.0000

Data Index: 1432037 (Python Code)

Max Activating Token Index: 52

Text #5

Max Range: 2.0460. Min Range: -2.0460

Max Act: 1.4971. Min Act: -0.0000

Data Index: 1577855 (Python Code)

Max Activating Token Index: 36

Text #6

Max Range: 2.0460. Min Range: -2.0460

Max Act: 1.5793. Min Act: -0.0000

Data Index: 1458245 (Python Code)

Max Activating Token Index: 251

Text #7

Max Range: 2.0460. Min Range: -2.0460

Max Act: 1.4633. Min Act: -0.0000

Data Index: 1594052 (Python Code)

Max Activating Token Index: 367

Text #8

Max Range: 2.0460. Min Range: -2.0460

Max Act: 1.3954. Min Act: -0.0000

Data Index: 1487631 (Python Code)

Max Activating Token Index: 392

Text #9

Max Range: 2.0460. Min Range: -2.0460

Max Act: 1.3904. Min Act: -0.0000

Data Index: 1609274 (Python Code)

Max Activating Token Index: 751

Text #10

Max Range: 2.0460. Min Range: -2.0460

Max Act: 1.4717. Min Act: -0.0000

Data Index: 1458270 (Python Code)

Max Activating Token Index: 618

Text #11

Max Range: 2.0460. Min Range: -2.0460

Max Act: 1.3333. Min Act: -0.0000

Data Index: 1488781 (Python Code)

Max Activating Token Index: 202

Text #12

Max Range: 2.0460. Min Range: -2.0460

Max Act: 1.4370. Min Act: -0.0000

Data Index: 1473531 (Python Code)

Max Activating Token Index: 88

Text #13

Max Range: 2.0460. Min Range: -2.0460

Max Act: 1.3914. Min Act: -0.0000

Data Index: 1600331 (Python Code)

Max Activating Token Index: 492

Text #14

Max Range: 2.0460. Min Range: -2.0460

Max Act: 1.4368. Min Act: -0.0000

Data Index: 1542176 (Python Code)

Max Activating Token Index: 123

Text #15

Max Range: 2.0460. Min Range: -2.0460

Max Act: 1.2953. Min Act: -0.0000

Data Index: 1380592 (Python Code)

Max Activating Token Index: 839

Text #16

Max Range: 2.0460. Min Range: -2.0460

Max Act: 1.3324. Min Act: -0.0000

Data Index: 1456212 (Python Code)

Max Activating Token Index: 169

Text #17

Max Range: 2.0460. Min Range: -2.0460

Max Act: 1.3404. Min Act: -0.0000

Data Index: 1377957 (Python Code)

Max Activating Token Index: 294

Text #18

Max Range: 2.0460. Min Range: -2.0460

Max Act: 1.4568. Min Act: -0.0000

Data Index: 1401850 (Python Code)

Max Activating Token Index: 127

Text #19

Max Range: 2.0460. Min Range: -2.0460

Max Act: 1.3275. Min Act: -0.0000

Data Index: 1518183 (Python Code)

Max Activating Token Index: 729