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

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

Neuron 5285 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: 0.5501. Min Range: -0.5501

Max Act: 0.5501. Min Act: -0.0002

Data Index: 1513046 (Python Code)

Max Activating Token Index: 4

Text #1

Max Range: 0.5501. Min Range: -0.5501

Max Act: 0.4913. Min Act: -0.0001

Data Index: 1396186 (Python Code)

Max Activating Token Index: 7

Text #2

Max Range: 0.5501. Min Range: -0.5501

Max Act: 0.4713. Min Act: -0.0002

Data Index: 1477807 (Python Code)

Max Activating Token Index: 4

Text #3

Max Range: 0.5501. Min Range: -0.5501

Max Act: 0.4714. Min Act: -0.0001

Data Index: 1618900 (Python Code)

Max Activating Token Index: 23

Text #4

Max Range: 0.5501. Min Range: -0.5501

Max Act: 0.4585. Min Act: -0.0001

Data Index: 1646058 (Python Code)

Max Activating Token Index: 174

Text #5

Max Range: 0.5501. Min Range: -0.5501

Max Act: 0.4669. Min Act: -0.0002

Data Index: 1374087 (Python Code)

Max Activating Token Index: 3

Text #6

Max Range: 0.5501. Min Range: -0.5501

Max Act: 0.4536. Min Act: -0.0001

Data Index: 1564370 (Python Code)

Max Activating Token Index: 3

Text #7

Max Range: 0.5501. Min Range: -0.5501

Max Act: 0.4465. Min Act: -0.0002

Data Index: 1563849 (Python Code)

Max Activating Token Index: 3

Text #8

Max Range: 0.5501. Min Range: -0.5501

Max Act: 0.4555. Min Act: -0.0001

Data Index: 1563885 (Python Code)

Max Activating Token Index: 75

Text #9

Max Range: 0.5501. Min Range: -0.5501

Max Act: 0.4498. Min Act: -0.0001

Data Index: 1433897 (Python Code)

Max Activating Token Index: 70

Text #10

Max Range: 0.5501. Min Range: -0.5501

Max Act: 0.4426. Min Act: -0.0001

Data Index: 1427225 (Python Code)

Max Activating Token Index: 21

Text #11

Max Range: 0.5501. Min Range: -0.5501

Max Act: 0.4417. Min Act: -0.0001

Data Index: 1455136 (Python Code)

Max Activating Token Index: 4

Text #12

Max Range: 0.5501. Min Range: -0.5501

Max Act: 0.4481. Min Act: -0.0001

Data Index: 1544960 (Python Code)

Max Activating Token Index: 3

Text #13

Max Range: 0.5501. Min Range: -0.5501

Max Act: 0.4411. Min Act: -0.0001

Data Index: 1436251 (Python Code)

Max Activating Token Index: 27

Text #14

Max Range: 0.5501. Min Range: -0.5501

Max Act: 0.4434. Min Act: -0.0001

Data Index: 1606557 (Python Code)

Max Activating Token Index: 241

Text #15

Max Range: 0.5501. Min Range: -0.5501

Max Act: 0.4460. Min Act: -0.0001

Data Index: 1408257 (Python Code)

Max Activating Token Index: 3

Text #16

Max Range: 0.5501. Min Range: -0.5501

Max Act: 0.4373. Min Act: -0.0001

Data Index: 1467815 (Python Code)

Max Activating Token Index: 235

Text #17

Max Range: 0.5501. Min Range: -0.5501

Max Act: 0.4390. Min Act: -0.0001

Data Index: 1525917 (Python Code)

Max Activating Token Index: 133

Text #18

Max Range: 0.5501. Min Range: -0.5501

Max Act: 0.4368. Min Act: -0.0001

Data Index: 1361093 (Python Code)

Max Activating Token Index: 377

Text #19

Max Range: 0.5501. Min Range: -0.5501

Max Act: 0.4427. Min Act: -0.0001

Data Index: 1539832 (Python Code)

Max Activating Token Index: 3