Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 848 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2602. Min Range: -0.2602

Max Act: 0.2602. Min Act: -0.0001

Data Index: 194577 (C4 (Web Text))

Max Activating Token Index: 89

Text #1

Max Range: 0.2602. Min Range: -0.2602

Max Act: 0.1874. Min Act: -0.0001

Data Index: 976818 (C4 (Web Text))

Max Activating Token Index: 64

Text #2

Max Range: 0.2602. Min Range: -0.2602

Max Act: 0.1908. Min Act: -0.0001

Data Index: 1571829 (Python Code)

Max Activating Token Index: 244

Text #3

Max Range: 0.2602. Min Range: -0.2602

Max Act: 0.1849. Min Act: -0.0001

Data Index: 352823 (C4 (Web Text))

Max Activating Token Index: 55

Text #4

Max Range: 0.2602. Min Range: -0.2602

Max Act: 0.1834. Min Act: -0.0001

Data Index: 820883 (C4 (Web Text))

Max Activating Token Index: 477

Text #5

Max Range: 0.2602. Min Range: -0.2602

Max Act: 0.1631. Min Act: -0.0001

Data Index: 751127 (C4 (Web Text))

Max Activating Token Index: 613

Text #6

Max Range: 0.2602. Min Range: -0.2602

Max Act: 0.1676. Min Act: -0.0001

Data Index: 494176 (C4 (Web Text))

Max Activating Token Index: 109

Text #7

Max Range: 0.2602. Min Range: -0.2602

Max Act: 0.1588. Min Act: -0.0001

Data Index: 344153 (C4 (Web Text))

Max Activating Token Index: 312

Text #8

Max Range: 0.2602. Min Range: -0.2602

Max Act: 0.1568. Min Act: -0.0001

Data Index: 1350517 (C4 (Web Text))

Max Activating Token Index: 189

Text #9

Max Range: 0.2602. Min Range: -0.2602

Max Act: 0.1600. Min Act: -0.0001

Data Index: 255300 (C4 (Web Text))

Max Activating Token Index: 125

Text #10

Max Range: 0.2602. Min Range: -0.2602

Max Act: 0.1524. Min Act: -0.0001

Data Index: 1053637 (C4 (Web Text))

Max Activating Token Index: 785

Text #11

Max Range: 0.2602. Min Range: -0.2602

Max Act: 0.1575. Min Act: -0.0001

Data Index: 216816 (C4 (Web Text))

Max Activating Token Index: 363

Text #12

Max Range: 0.2602. Min Range: -0.2602

Max Act: 0.1558. Min Act: -0.0001

Data Index: 1081457 (C4 (Web Text))

Max Activating Token Index: 439

Text #13

Max Range: 0.2602. Min Range: -0.2602

Max Act: 0.1382. Min Act: -0.0001

Data Index: 567022 (C4 (Web Text))

Max Activating Token Index: 613

Text #14

Max Range: 0.2602. Min Range: -0.2602

Max Act: 0.1501. Min Act: -0.0001

Data Index: 1106210 (C4 (Web Text))

Max Activating Token Index: 951

Text #15

Max Range: 0.2602. Min Range: -0.2602

Max Act: 0.1494. Min Act: -0.0001

Data Index: 1061474 (C4 (Web Text))

Max Activating Token Index: 731

Text #16

Max Range: 0.2602. Min Range: -0.2602

Max Act: 0.1486. Min Act: -0.0001

Data Index: 193358 (C4 (Web Text))

Max Activating Token Index: 29

Text #17

Max Range: 0.2602. Min Range: -0.2602

Max Act: 0.1567. Min Act: -0.0001

Data Index: 400381 (C4 (Web Text))

Max Activating Token Index: 281

Text #18

Max Range: 0.2602. Min Range: -0.2602

Max Act: 0.1470. Min Act: -0.0001

Data Index: 692985 (C4 (Web Text))

Max Activating Token Index: 336

Text #19

Max Range: 0.2602. Min Range: -0.2602

Max Act: 0.1368. Min Act: -0.0001

Data Index: 321755 (C4 (Web Text))

Max Activating Token Index: 240