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

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

Neuron 6095 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.6535. Min Range: -5.6535

Max Act: 5.6535. Min Act: -0.0000

Data Index: 1042644 (C4 (Web Text))

Max Activating Token Index: 837

Text #1

Max Range: 5.6535. Min Range: -5.6535

Max Act: 4.9044. Min Act: -0.0000

Data Index: 463964 (C4 (Web Text))

Max Activating Token Index: 312

Text #2

Max Range: 5.6535. Min Range: -5.6535

Max Act: 4.8780. Min Act: -0.0000

Data Index: 6870 (C4 (Web Text))

Max Activating Token Index: 1015

Text #3

Max Range: 5.6535. Min Range: -5.6535

Max Act: 4.4796. Min Act: -0.0000

Data Index: 230188 (C4 (Web Text))

Max Activating Token Index: 170

Text #4

Max Range: 5.6535. Min Range: -5.6535

Max Act: 4.2892. Min Act: -0.0000

Data Index: 1180526 (C4 (Web Text))

Max Activating Token Index: 445

Text #5

Max Range: 5.6535. Min Range: -5.6535

Max Act: 4.6256. Min Act: -0.0000

Data Index: 1538487 (Python Code)

Max Activating Token Index: 463

Text #6

Max Range: 5.6535. Min Range: -5.6535

Max Act: 4.0863. Min Act: -0.0000

Data Index: 1442225 (Python Code)

Max Activating Token Index: 366

Text #7

Max Range: 5.6535. Min Range: -5.6535

Max Act: 3.9355. Min Act: -0.0000

Data Index: 1448060 (Python Code)

Max Activating Token Index: 60

Text #8

Max Range: 5.6535. Min Range: -5.6535

Max Act: 4.0719. Min Act: -0.0000

Data Index: 1375403 (Python Code)

Max Activating Token Index: 12

Text #9

Max Range: 5.6535. Min Range: -5.6535

Max Act: 3.8443. Min Act: -0.0000

Data Index: 1322817 (C4 (Web Text))

Max Activating Token Index: 565

Text #10

Max Range: 5.6535. Min Range: -5.6535

Max Act: 3.8397. Min Act: -0.0000

Data Index: 811966 (C4 (Web Text))

Max Activating Token Index: 746

Text #11

Max Range: 5.6535. Min Range: -5.6535

Max Act: 3.8592. Min Act: -0.0000

Data Index: 730079 (C4 (Web Text))

Max Activating Token Index: 773

Text #12

Max Range: 5.6535. Min Range: -5.6535

Max Act: 3.6617. Min Act: -0.0000

Data Index: 1591475 (Python Code)

Max Activating Token Index: 848

Text #13

Max Range: 5.6535. Min Range: -5.6535

Max Act: 3.6580. Min Act: -0.0000

Data Index: 908665 (C4 (Web Text))

Max Activating Token Index: 896

Text #14

Max Range: 5.6535. Min Range: -5.6535

Max Act: 3.5958. Min Act: -0.0000

Data Index: 294656 (C4 (Web Text))

Max Activating Token Index: 757

Text #15

Max Range: 5.6535. Min Range: -5.6535

Max Act: 3.7626. Min Act: -0.0000

Data Index: 712647 (C4 (Web Text))

Max Activating Token Index: 497

Text #16

Max Range: 5.6535. Min Range: -5.6535

Max Act: 3.5775. Min Act: -0.0000

Data Index: 1554557 (Python Code)

Max Activating Token Index: 274

Text #17

Max Range: 5.6535. Min Range: -5.6535

Max Act: 3.7201. Min Act: -0.0000

Data Index: 1374671 (Python Code)

Max Activating Token Index: 824

Text #18

Max Range: 5.6535. Min Range: -5.6535

Max Act: 3.6780. Min Act: -0.0000

Data Index: 321416 (C4 (Web Text))

Max Activating Token Index: 782

Text #19

Max Range: 5.6535. Min Range: -5.6535

Max Act: 3.5481. Min Act: -0.0000

Data Index: 99255 (C4 (Web Text))

Max Activating Token Index: 337