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

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

Neuron 1543 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9384. Min Range: -0.9384

Max Act: 0.9384. Min Act: -0.0000

Data Index: 1556654 (Python Code)

Max Activating Token Index: 80

Text #1

Max Range: 0.9384. Min Range: -0.9384

Max Act: 0.8706. Min Act: -0.0000

Data Index: 1436007 (Python Code)

Max Activating Token Index: 106

Text #2

Max Range: 0.9384. Min Range: -0.9384

Max Act: 0.8906. Min Act: -0.0000

Data Index: 1615899 (Python Code)

Max Activating Token Index: 11

Text #3

Max Range: 0.9384. Min Range: -0.9384

Max Act: 0.8429. Min Act: -0.0000

Data Index: 1406764 (Python Code)

Max Activating Token Index: 192

Text #4

Max Range: 0.9384. Min Range: -0.9384

Max Act: 0.8056. Min Act: -0.0000

Data Index: 1612317 (Python Code)

Max Activating Token Index: 15

Text #5

Max Range: 0.9384. Min Range: -0.9384

Max Act: 0.7663. Min Act: -0.0000

Data Index: 1521087 (Python Code)

Max Activating Token Index: 6

Text #6

Max Range: 0.9384. Min Range: -0.9384

Max Act: 0.7726. Min Act: -0.0000

Data Index: 1490414 (Python Code)

Max Activating Token Index: 16

Text #7

Max Range: 0.9384. Min Range: -0.9384

Max Act: 0.7046. Min Act: -0.0000

Data Index: 1607946 (Python Code)

Max Activating Token Index: 39

Text #8

Max Range: 0.9384. Min Range: -0.9384

Max Act: 0.8635. Min Act: -0.0000

Data Index: 1471056 (Python Code)

Max Activating Token Index: 128

Text #9

Max Range: 0.9384. Min Range: -0.9384

Max Act: 0.7684. Min Act: -0.0000

Data Index: 1503873 (Python Code)

Max Activating Token Index: 18

Text #10

Max Range: 0.9384. Min Range: -0.9384

Max Act: 0.6733. Min Act: -0.0000

Data Index: 1477754 (Python Code)

Max Activating Token Index: 98

Text #11

Max Range: 0.9384. Min Range: -0.9384

Max Act: 0.6507. Min Act: -0.0000

Data Index: 1604652 (Python Code)

Max Activating Token Index: 323

Text #12

Max Range: 0.9384. Min Range: -0.9384

Max Act: 0.6677. Min Act: -0.0000

Data Index: 1581034 (Python Code)

Max Activating Token Index: 112

Text #13

Max Range: 0.9384. Min Range: -0.9384

Max Act: 0.6033. Min Act: -0.0000

Data Index: 1631255 (Python Code)

Max Activating Token Index: 163

Text #14

Max Range: 0.9384. Min Range: -0.9384

Max Act: 0.6413. Min Act: -0.0000

Data Index: 1494222 (Python Code)

Max Activating Token Index: 68

Text #15

Max Range: 0.9384. Min Range: -0.9384

Max Act: 0.7049. Min Act: -0.0000

Data Index: 1605951 (Python Code)

Max Activating Token Index: 67

Text #16

Max Range: 0.9384. Min Range: -0.9384

Max Act: 0.6359. Min Act: -0.0000

Data Index: 1616295 (Python Code)

Max Activating Token Index: 539

Text #17

Max Range: 0.9384. Min Range: -0.9384

Max Act: 0.6100. Min Act: -0.0000

Data Index: 107941 (C4 (Web Text))

Max Activating Token Index: 814

Text #18

Max Range: 0.9384. Min Range: -0.9384

Max Act: 0.6702. Min Act: -0.0000

Data Index: 1382304 (Python Code)

Max Activating Token Index: 12

Text #19

Max Range: 0.9384. Min Range: -0.9384

Max Act: 0.6258. Min Act: -0.0000

Data Index: 1439147 (Python Code)

Max Activating Token Index: 93