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

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

Neuron 4260 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5834. Min Range: -0.5834

Max Act: 0.5834. Min Act: -0.0001

Data Index: 1588529 (Python Code)

Max Activating Token Index: 1022

Text #1

Max Range: 0.5834. Min Range: -0.5834

Max Act: 0.4904. Min Act: -0.0001

Data Index: 1440970 (Python Code)

Max Activating Token Index: 54

Text #2

Max Range: 0.5834. Min Range: -0.5834

Max Act: 0.4726. Min Act: -0.0001

Data Index: 1369475 (Python Code)

Max Activating Token Index: 330

Text #3

Max Range: 0.5834. Min Range: -0.5834

Max Act: 0.4814. Min Act: -0.0001

Data Index: 1522963 (Python Code)

Max Activating Token Index: 457

Text #4

Max Range: 0.5834. Min Range: -0.5834

Max Act: 0.4756. Min Act: -0.0001

Data Index: 1642468 (Python Code)

Max Activating Token Index: 792

Text #5

Max Range: 0.5834. Min Range: -0.5834

Max Act: 0.4508. Min Act: -0.0001

Data Index: 1403499 (Python Code)

Max Activating Token Index: 287

Text #6

Max Range: 0.5834. Min Range: -0.5834

Max Act: 0.4369. Min Act: -0.0001

Data Index: 1502131 (Python Code)

Max Activating Token Index: 140

Text #7

Max Range: 0.5834. Min Range: -0.5834

Max Act: 0.3978. Min Act: -0.0001

Data Index: 1602164 (Python Code)

Max Activating Token Index: 283

Text #8

Max Range: 0.5834. Min Range: -0.5834

Max Act: 0.4009. Min Act: -0.0001

Data Index: 1513035 (Python Code)

Max Activating Token Index: 48

Text #9

Max Range: 0.5834. Min Range: -0.5834

Max Act: 0.4042. Min Act: -0.0001

Data Index: 1606447 (Python Code)

Max Activating Token Index: 373

Text #10

Max Range: 0.5834. Min Range: -0.5834

Max Act: 0.3792. Min Act: -0.0001

Data Index: 1604572 (Python Code)

Max Activating Token Index: 54

Text #11

Max Range: 0.5834. Min Range: -0.5834

Max Act: 0.4453. Min Act: -0.0001

Data Index: 1412442 (Python Code)

Max Activating Token Index: 83

Text #12

Max Range: 0.5834. Min Range: -0.5834

Max Act: 0.3892. Min Act: -0.0001

Data Index: 1547503 (Python Code)

Max Activating Token Index: 425

Text #13

Max Range: 0.5834. Min Range: -0.5834

Max Act: 0.3907. Min Act: -0.0001

Data Index: 1622495 (Python Code)

Max Activating Token Index: 800

Text #14

Max Range: 0.5834. Min Range: -0.5834

Max Act: 0.3854. Min Act: -0.0001

Data Index: 1426828 (Python Code)

Max Activating Token Index: 124

Text #15

Max Range: 0.5834. Min Range: -0.5834

Max Act: 0.4235. Min Act: -0.0001

Data Index: 1616888 (Python Code)

Max Activating Token Index: 787

Text #16

Max Range: 0.5834. Min Range: -0.5834

Max Act: 0.3809. Min Act: -0.0001

Data Index: 1592501 (Python Code)

Max Activating Token Index: 768

Text #17

Max Range: 0.5834. Min Range: -0.5834

Max Act: 0.3911. Min Act: -0.0001

Data Index: 1637317 (Python Code)

Max Activating Token Index: 375

Text #18

Max Range: 0.5834. Min Range: -0.5834

Max Act: 0.3607. Min Act: -0.0001

Data Index: 1654667 (Python Code)

Max Activating Token Index: 639

Text #19

Max Range: 0.5834. Min Range: -0.5834

Max Act: 0.4033. Min Act: -0.0001

Data Index: 1587272 (Python Code)

Max Activating Token Index: 18