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

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

Neuron 4370 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7147. Min Range: -1.7147

Max Act: 1.6589. Min Act: -0.0000

Data Index: 1325676 (C4 (Web Text))

Max Activating Token Index: 738

Text #1

Max Range: 1.7147. Min Range: -1.7147

Max Act: 1.6417. Min Act: -0.0000

Data Index: 805921 (C4 (Web Text))

Max Activating Token Index: 277

Text #2

Max Range: 1.7147. Min Range: -1.7147

Max Act: 1.5526. Min Act: -0.0000

Data Index: 1591659 (Python Code)

Max Activating Token Index: 594

Text #3

Max Range: 1.7147. Min Range: -1.7147

Max Act: 1.7111. Min Act: -0.0000

Data Index: 1413352 (Python Code)

Max Activating Token Index: 757

Text #4

Max Range: 1.7147. Min Range: -1.7147

Max Act: 1.7147. Min Act: -0.0000

Data Index: 924633 (C4 (Web Text))

Max Activating Token Index: 891

Text #5

Max Range: 1.7147. Min Range: -1.7147

Max Act: 1.4739. Min Act: -0.0000

Data Index: 81839 (C4 (Web Text))

Max Activating Token Index: 607

Text #6

Max Range: 1.7147. Min Range: -1.7147

Max Act: 1.5680. Min Act: -0.0000

Data Index: 557849 (C4 (Web Text))

Max Activating Token Index: 333

Text #7

Max Range: 1.7147. Min Range: -1.7147

Max Act: 1.5132. Min Act: -0.0000

Data Index: 1443195 (Python Code)

Max Activating Token Index: 850

Text #8

Max Range: 1.7147. Min Range: -1.7147

Max Act: 1.5109. Min Act: -0.0000

Data Index: 1408259 (Python Code)

Max Activating Token Index: 906

Text #9

Max Range: 1.7147. Min Range: -1.7147

Max Act: 1.4084. Min Act: -0.0000

Data Index: 1098038 (C4 (Web Text))

Max Activating Token Index: 996

Text #10

Max Range: 1.7147. Min Range: -1.7147

Max Act: 1.4475. Min Act: -0.0000

Data Index: 1502596 (Python Code)

Max Activating Token Index: 143

Text #11

Max Range: 1.7147. Min Range: -1.7147

Max Act: 1.4349. Min Act: -0.0000

Data Index: 1051334 (C4 (Web Text))

Max Activating Token Index: 507

Text #12

Max Range: 1.7147. Min Range: -1.7147

Max Act: 1.3984. Min Act: -0.0000

Data Index: 121669 (C4 (Web Text))

Max Activating Token Index: 553

Text #13

Max Range: 1.7147. Min Range: -1.7147

Max Act: 1.3355. Min Act: -0.0000

Data Index: 1555661 (Python Code)

Max Activating Token Index: 682

Text #14

Max Range: 1.7147. Min Range: -1.7147

Max Act: 1.3941. Min Act: -0.0000

Data Index: 1062784 (C4 (Web Text))

Max Activating Token Index: 8

Text #15

Max Range: 1.7147. Min Range: -1.7147

Max Act: 1.3167. Min Act: -0.0000

Data Index: 755130 (C4 (Web Text))

Max Activating Token Index: 557

Text #16

Max Range: 1.7147. Min Range: -1.7147

Max Act: 1.3093. Min Act: -0.0000

Data Index: 1139584 (C4 (Web Text))

Max Activating Token Index: 17

Text #17

Max Range: 1.7147. Min Range: -1.7147

Max Act: 1.2779. Min Act: -0.0000

Data Index: 127628 (C4 (Web Text))

Max Activating Token Index: 942

Text #18

Max Range: 1.7147. Min Range: -1.7147

Max Act: 1.3418. Min Act: -0.0000

Data Index: 143295 (C4 (Web Text))

Max Activating Token Index: 217

Text #19

Max Range: 1.7147. Min Range: -1.7147

Max Act: 1.2067. Min Act: -0.0000

Data Index: 579000 (C4 (Web Text))

Max Activating Token Index: 379