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

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

Neuron 3732 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8700. Min Range: -1.8700

Max Act: 1.8700. Min Act: -0.0001

Data Index: 1539062 (Python Code)

Max Activating Token Index: 656

Text #1

Max Range: 1.8700. Min Range: -1.8700

Max Act: 1.8393. Min Act: -0.0001

Data Index: 1647590 (Python Code)

Max Activating Token Index: 985

Text #2

Max Range: 1.8700. Min Range: -1.8700

Max Act: 1.7331. Min Act: -0.0001

Data Index: 1533333 (Python Code)

Max Activating Token Index: 429

Text #3

Max Range: 1.8700. Min Range: -1.8700

Max Act: 1.7255. Min Act: -0.0001

Data Index: 1649416 (Python Code)

Max Activating Token Index: 959

Text #4

Max Range: 1.8700. Min Range: -1.8700

Max Act: 1.7476. Min Act: -0.0000

Data Index: 1380057 (Python Code)

Max Activating Token Index: 678

Text #5

Max Range: 1.8700. Min Range: -1.8700

Max Act: 1.6323. Min Act: -0.0000

Data Index: 1428469 (Python Code)

Max Activating Token Index: 125

Text #6

Max Range: 1.8700. Min Range: -1.8700

Max Act: 1.3485. Min Act: -0.0000

Data Index: 1469635 (Python Code)

Max Activating Token Index: 753

Text #7

Max Range: 1.8700. Min Range: -1.8700

Max Act: 1.5509. Min Act: -0.0001

Data Index: 1519218 (Python Code)

Max Activating Token Index: 774

Text #8

Max Range: 1.8700. Min Range: -1.8700

Max Act: 1.5048. Min Act: -0.0001

Data Index: 1499318 (Python Code)

Max Activating Token Index: 270

Text #9

Max Range: 1.8700. Min Range: -1.8700

Max Act: 1.5337. Min Act: -0.0001

Data Index: 1512161 (Python Code)

Max Activating Token Index: 689

Text #10

Max Range: 1.8700. Min Range: -1.8700

Max Act: 1.4805. Min Act: -0.0000

Data Index: 1415353 (Python Code)

Max Activating Token Index: 928

Text #11

Max Range: 1.8700. Min Range: -1.8700

Max Act: 1.4389. Min Act: -0.0001

Data Index: 1418926 (Python Code)

Max Activating Token Index: 888

Text #12

Max Range: 1.8700. Min Range: -1.8700

Max Act: 1.4359. Min Act: -0.0000

Data Index: 1383453 (Python Code)

Max Activating Token Index: 740

Text #13

Max Range: 1.8700. Min Range: -1.8700

Max Act: 1.5081. Min Act: -0.0001

Data Index: 1542448 (Python Code)

Max Activating Token Index: 981

Text #14

Max Range: 1.8700. Min Range: -1.8700

Max Act: 1.3920. Min Act: -0.0001

Data Index: 1560594 (Python Code)

Max Activating Token Index: 656

Text #15

Max Range: 1.8700. Min Range: -1.8700

Max Act: 1.4111. Min Act: -0.0001

Data Index: 1375105 (Python Code)

Max Activating Token Index: 626

Text #16

Max Range: 1.8700. Min Range: -1.8700

Max Act: 1.4033. Min Act: -0.0001

Data Index: 1407184 (Python Code)

Max Activating Token Index: 880

Text #17

Max Range: 1.8700. Min Range: -1.8700

Max Act: 1.3181. Min Act: -0.0001

Data Index: 1629662 (Python Code)

Max Activating Token Index: 216

Text #18

Max Range: 1.8700. Min Range: -1.8700

Max Act: 1.3576. Min Act: -0.0001

Data Index: 1434359 (Python Code)

Max Activating Token Index: 504

Text #19

Max Range: 1.8700. Min Range: -1.8700

Max Act: 1.4701. Min Act: -0.0000

Data Index: 1606937 (Python Code)

Max Activating Token Index: 441