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

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

Neuron 4380 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0719. Min Range: -0.0719

Max Act: 0.0719. Min Act: -0.0001

Data Index: 1302604 (C4 (Web Text))

Max Activating Token Index: 243

Text #1

Max Range: 0.0719. Min Range: -0.0719

Max Act: 0.0627. Min Act: -0.0000

Data Index: 41097 (C4 (Web Text))

Max Activating Token Index: 897

Text #2

Max Range: 0.0719. Min Range: -0.0719

Max Act: 0.0665. Min Act: -0.0000

Data Index: 840148 (C4 (Web Text))

Max Activating Token Index: 672

Text #3

Max Range: 0.0719. Min Range: -0.0719

Max Act: 0.0633. Min Act: -0.0000

Data Index: 486075 (C4 (Web Text))

Max Activating Token Index: 365

Text #4

Max Range: 0.0719. Min Range: -0.0719

Max Act: 0.0586. Min Act: -0.0000

Data Index: 1351771 (C4 (Web Text))

Max Activating Token Index: 370

Text #5

Max Range: 0.0719. Min Range: -0.0719

Max Act: 0.0632. Min Act: -0.0001

Data Index: 100352 (C4 (Web Text))

Max Activating Token Index: 335

Text #6

Max Range: 0.0719. Min Range: -0.0719

Max Act: 0.0614. Min Act: -0.0000

Data Index: 1316537 (C4 (Web Text))

Max Activating Token Index: 963

Text #7

Max Range: 0.0719. Min Range: -0.0719

Max Act: 0.0614. Min Act: -0.0000

Data Index: 721172 (C4 (Web Text))

Max Activating Token Index: 730

Text #8

Max Range: 0.0719. Min Range: -0.0719

Max Act: 0.0586. Min Act: -0.0001

Data Index: 1096899 (C4 (Web Text))

Max Activating Token Index: 513

Text #9

Max Range: 0.0719. Min Range: -0.0719

Max Act: 0.0608. Min Act: -0.0000

Data Index: 727857 (C4 (Web Text))

Max Activating Token Index: 243

Text #10

Max Range: 0.0719. Min Range: -0.0719

Max Act: 0.0590. Min Act: -0.0000

Data Index: 1007619 (C4 (Web Text))

Max Activating Token Index: 576

Text #11

Max Range: 0.0719. Min Range: -0.0719

Max Act: 0.0565. Min Act: -0.0000

Data Index: 925667 (C4 (Web Text))

Max Activating Token Index: 589

Text #12

Max Range: 0.0719. Min Range: -0.0719

Max Act: 0.0566. Min Act: -0.0000

Data Index: 216831 (C4 (Web Text))

Max Activating Token Index: 347

Text #13

Max Range: 0.0719. Min Range: -0.0719

Max Act: 0.0565. Min Act: -0.0000

Data Index: 1217379 (C4 (Web Text))

Max Activating Token Index: 831

Text #14

Max Range: 0.0719. Min Range: -0.0719

Max Act: 0.0580. Min Act: -0.0000

Data Index: 719586 (C4 (Web Text))

Max Activating Token Index: 805

Text #15

Max Range: 0.0719. Min Range: -0.0719

Max Act: 0.0516. Min Act: -0.0000

Data Index: 872081 (C4 (Web Text))

Max Activating Token Index: 661

Text #16

Max Range: 0.0719. Min Range: -0.0719

Max Act: 0.0525. Min Act: -0.0000

Data Index: 837977 (C4 (Web Text))

Max Activating Token Index: 54

Text #17

Max Range: 0.0719. Min Range: -0.0719

Max Act: 0.0499. Min Act: -0.0000

Data Index: 1018411 (C4 (Web Text))

Max Activating Token Index: 85

Text #18

Max Range: 0.0719. Min Range: -0.0719

Max Act: 0.0539. Min Act: -0.0001

Data Index: 772618 (C4 (Web Text))

Max Activating Token Index: 370

Text #19

Max Range: 0.0719. Min Range: -0.0719

Max Act: 0.0562. Min Act: -0.0000

Data Index: 1025777 (C4 (Web Text))

Max Activating Token Index: 609