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

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

Neuron 2081 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2031. Min Range: -1.2031

Max Act: 1.2031. Min Act: -0.0000

Data Index: 1534445 (Python Code)

Max Activating Token Index: 1008

Text #1

Max Range: 1.2031. Min Range: -1.2031

Max Act: 1.0330. Min Act: -0.0000

Data Index: 1415026 (Python Code)

Max Activating Token Index: 906

Text #2

Max Range: 1.2031. Min Range: -1.2031

Max Act: 1.0159. Min Act: -0.0000

Data Index: 1375483 (Python Code)

Max Activating Token Index: 60

Text #3

Max Range: 1.2031. Min Range: -1.2031

Max Act: 0.9595. Min Act: -0.0000

Data Index: 1561274 (Python Code)

Max Activating Token Index: 733

Text #4

Max Range: 1.2031. Min Range: -1.2031

Max Act: 0.9682. Min Act: -0.0000

Data Index: 1471879 (Python Code)

Max Activating Token Index: 1016

Text #5

Max Range: 1.2031. Min Range: -1.2031

Max Act: 0.9197. Min Act: -0.0000

Data Index: 1588262 (Python Code)

Max Activating Token Index: 270

Text #6

Max Range: 1.2031. Min Range: -1.2031

Max Act: 0.9736. Min Act: -0.0000

Data Index: 1367358 (Python Code)

Max Activating Token Index: 295

Text #7

Max Range: 1.2031. Min Range: -1.2031

Max Act: 0.9340. Min Act: -0.0000

Data Index: 1549587 (Python Code)

Max Activating Token Index: 957

Text #8

Max Range: 1.2031. Min Range: -1.2031

Max Act: 0.9615. Min Act: -0.0000

Data Index: 1636679 (Python Code)

Max Activating Token Index: 168

Text #9

Max Range: 1.2031. Min Range: -1.2031

Max Act: 0.9235. Min Act: -0.0000

Data Index: 1394762 (Python Code)

Max Activating Token Index: 390

Text #10

Max Range: 1.2031. Min Range: -1.2031

Max Act: 0.9173. Min Act: 0.0000

Data Index: 1533199 (Python Code)

Max Activating Token Index: 92

Text #11

Max Range: 1.2031. Min Range: -1.2031

Max Act: 0.9090. Min Act: -0.0000

Data Index: 1392060 (Python Code)

Max Activating Token Index: 489

Text #12

Max Range: 1.2031. Min Range: -1.2031

Max Act: 0.8929. Min Act: 0.0000

Data Index: 1479993 (Python Code)

Max Activating Token Index: 649

Text #13

Max Range: 1.2031. Min Range: -1.2031

Max Act: 0.8674. Min Act: -0.0000

Data Index: 1588719 (Python Code)

Max Activating Token Index: 523

Text #14

Max Range: 1.2031. Min Range: -1.2031

Max Act: 0.9229. Min Act: 0.0000

Data Index: 1501369 (Python Code)

Max Activating Token Index: 840

Text #15

Max Range: 1.2031. Min Range: -1.2031

Max Act: 0.8545. Min Act: -0.0000

Data Index: 1578064 (Python Code)

Max Activating Token Index: 623

Text #16

Max Range: 1.2031. Min Range: -1.2031

Max Act: 0.8792. Min Act: 0.0000

Data Index: 1550227 (Python Code)

Max Activating Token Index: 1016

Text #17

Max Range: 1.2031. Min Range: -1.2031

Max Act: 0.8236. Min Act: 0.0000

Data Index: 1373629 (Python Code)

Max Activating Token Index: 69

Text #18

Max Range: 1.2031. Min Range: -1.2031

Max Act: 0.8729. Min Act: 0.0000

Data Index: 1467011 (Python Code)

Max Activating Token Index: 226

Text #19

Max Range: 1.2031. Min Range: -1.2031

Max Act: 0.8963. Min Act: -0.0000

Data Index: 1369798 (Python Code)

Max Activating Token Index: 265