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

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

Neuron 4728 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0891. Min Act: -0.0001

Data Index: 1318742 (C4 (Web Text))

Max Activating Token Index: 624

Text #1

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0855. Min Act: -0.0000

Data Index: 1583541 (Python Code)

Max Activating Token Index: 298

Text #2

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0722. Min Act: -0.0000

Data Index: 923388 (C4 (Web Text))

Max Activating Token Index: 328

Text #3

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0663. Min Act: -0.0000

Data Index: 166768 (C4 (Web Text))

Max Activating Token Index: 93

Text #4

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0682. Min Act: -0.0001

Data Index: 1018023 (C4 (Web Text))

Max Activating Token Index: 290

Text #5

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0622. Min Act: -0.0001

Data Index: 1439215 (Python Code)

Max Activating Token Index: 913

Text #6

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0665. Min Act: -0.0001

Data Index: 899344 (C4 (Web Text))

Max Activating Token Index: 315

Text #7

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0635. Min Act: -0.0000

Data Index: 1452385 (Python Code)

Max Activating Token Index: 744

Text #8

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0611. Min Act: -0.0000

Data Index: 366169 (C4 (Web Text))

Max Activating Token Index: 128

Text #9

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0704. Min Act: -0.0000

Data Index: 1233474 (C4 (Web Text))

Max Activating Token Index: 667

Text #10

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0567. Min Act: -0.0000

Data Index: 537390 (C4 (Web Text))

Max Activating Token Index: 574

Text #11

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0525. Min Act: -0.0000

Data Index: 1373555 (Python Code)

Max Activating Token Index: 996

Text #12

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0501. Min Act: -0.0000

Data Index: 1550313 (Python Code)

Max Activating Token Index: 964

Text #13

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0527. Min Act: -0.0001

Data Index: 52294 (C4 (Web Text))

Max Activating Token Index: 250

Text #14

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0479. Min Act: -0.0000

Data Index: 83457 (C4 (Web Text))

Max Activating Token Index: 285

Text #15

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0560. Min Act: -0.0000

Data Index: 55187 (C4 (Web Text))

Max Activating Token Index: 353

Text #16

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0513. Min Act: -0.0001

Data Index: 1485545 (Python Code)

Max Activating Token Index: 577

Text #17

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0503. Min Act: -0.0000

Data Index: 37554 (C4 (Web Text))

Max Activating Token Index: 347

Text #18

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0525. Min Act: -0.0001

Data Index: 845002 (C4 (Web Text))

Max Activating Token Index: 71

Text #19

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0512. Min Act: -0.0000

Data Index: 293683 (C4 (Web Text))

Max Activating Token Index: 359