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

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

Neuron 5110 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5494. Min Range: -1.5494

Max Act: 1.5494. Min Act: -0.0000

Data Index: 681320 (C4 (Web Text))

Max Activating Token Index: 1007

Text #1

Max Range: 1.5494. Min Range: -1.5494

Max Act: 1.3642. Min Act: -0.0000

Data Index: 1307655 (C4 (Web Text))

Max Activating Token Index: 719

Text #2

Max Range: 1.5494. Min Range: -1.5494

Max Act: 1.3564. Min Act: -0.0000

Data Index: 630487 (C4 (Web Text))

Max Activating Token Index: 454

Text #3

Max Range: 1.5494. Min Range: -1.5494

Max Act: 1.3030. Min Act: -0.0000

Data Index: 485542 (C4 (Web Text))

Max Activating Token Index: 238

Text #4

Max Range: 1.5494. Min Range: -1.5494

Max Act: 1.0560. Min Act: -0.0000

Data Index: 1413664 (Python Code)

Max Activating Token Index: 190

Text #5

Max Range: 1.5494. Min Range: -1.5494

Max Act: 0.9910. Min Act: -0.0000

Data Index: 1656137 (Python Code)

Max Activating Token Index: 614

Text #6

Max Range: 1.5494. Min Range: -1.5494

Max Act: 0.9246. Min Act: -0.0000

Data Index: 1487511 (Python Code)

Max Activating Token Index: 380

Text #7

Max Range: 1.5494. Min Range: -1.5494

Max Act: 0.9176. Min Act: -0.0000

Data Index: 196545 (C4 (Web Text))

Max Activating Token Index: 389

Text #8

Max Range: 1.5494. Min Range: -1.5494

Max Act: 0.9450. Min Act: -0.0000

Data Index: 1405254 (Python Code)

Max Activating Token Index: 910

Text #9

Max Range: 1.5494. Min Range: -1.5494

Max Act: 0.8745. Min Act: -0.0000

Data Index: 1378365 (Python Code)

Max Activating Token Index: 944

Text #10

Max Range: 1.5494. Min Range: -1.5494

Max Act: 0.9302. Min Act: -0.0000

Data Index: 1624675 (Python Code)

Max Activating Token Index: 597

Text #11

Max Range: 1.5494. Min Range: -1.5494

Max Act: 0.8858. Min Act: -0.0000

Data Index: 119619 (C4 (Web Text))

Max Activating Token Index: 215

Text #12

Max Range: 1.5494. Min Range: -1.5494

Max Act: 0.9017. Min Act: -0.0000

Data Index: 1435240 (Python Code)

Max Activating Token Index: 923

Text #13

Max Range: 1.5494. Min Range: -1.5494

Max Act: 0.9371. Min Act: -0.0000

Data Index: 1557386 (Python Code)

Max Activating Token Index: 147

Text #14

Max Range: 1.5494. Min Range: -1.5494

Max Act: 0.9189. Min Act: -0.0000

Data Index: 1454246 (Python Code)

Max Activating Token Index: 364

Text #15

Max Range: 1.5494. Min Range: -1.5494

Max Act: 0.8673. Min Act: -0.0000

Data Index: 1483372 (Python Code)

Max Activating Token Index: 687

Text #16

Max Range: 1.5494. Min Range: -1.5494

Max Act: 0.8624. Min Act: -0.0000

Data Index: 1412731 (Python Code)

Max Activating Token Index: 835

Text #17

Max Range: 1.5494. Min Range: -1.5494

Max Act: 0.8828. Min Act: -0.0000

Data Index: 1603433 (Python Code)

Max Activating Token Index: 1000

Text #18

Max Range: 1.5494. Min Range: -1.5494

Max Act: 0.8177. Min Act: -0.0000

Data Index: 1579401 (Python Code)

Max Activating Token Index: 970

Text #19

Max Range: 1.5494. Min Range: -1.5494

Max Act: 0.8594. Min Act: -0.0000

Data Index: 1422787 (Python Code)

Max Activating Token Index: 417