Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 554 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 4.9121. Min Range: -4.9121

Max Act: 4.7818. Min Act: -0.0001

Data Index: 160068 (C4 (Web Text))

Max Activating Token Index: 753

Text #1

Max Range: 4.9121. Min Range: -4.9121

Max Act: 4.9121. Min Act: -0.0001

Data Index: 1298657 (C4 (Web Text))

Max Activating Token Index: 756

Text #2

Max Range: 4.9121. Min Range: -4.9121

Max Act: 4.4249. Min Act: -0.0001

Data Index: 635614 (C4 (Web Text))

Max Activating Token Index: 605

Text #3

Max Range: 4.9121. Min Range: -4.9121

Max Act: 4.4506. Min Act: -0.0001

Data Index: 1285597 (C4 (Web Text))

Max Activating Token Index: 16

Text #4

Max Range: 4.9121. Min Range: -4.9121

Max Act: 4.3297. Min Act: -0.0001

Data Index: 1290508 (C4 (Web Text))

Max Activating Token Index: 164

Text #5

Max Range: 4.9121. Min Range: -4.9121

Max Act: 3.8297. Min Act: -0.0001

Data Index: 1277062 (C4 (Web Text))

Max Activating Token Index: 371

Text #6

Max Range: 4.9121. Min Range: -4.9121

Max Act: 4.0842. Min Act: -0.0001

Data Index: 372565 (C4 (Web Text))

Max Activating Token Index: 957

Text #7

Max Range: 4.9121. Min Range: -4.9121

Max Act: 4.2926. Min Act: -0.0001

Data Index: 779218 (C4 (Web Text))

Max Activating Token Index: 684

Text #8

Max Range: 4.9121. Min Range: -4.9121

Max Act: 4.0074. Min Act: -0.0001

Data Index: 414898 (C4 (Web Text))

Max Activating Token Index: 39

Text #9

Max Range: 4.9121. Min Range: -4.9121

Max Act: 3.7254. Min Act: -0.0001

Data Index: 9932 (C4 (Web Text))

Max Activating Token Index: 83

Text #10

Max Range: 4.9121. Min Range: -4.9121

Max Act: 3.6792. Min Act: -0.0001

Data Index: 925303 (C4 (Web Text))

Max Activating Token Index: 984

Text #11

Max Range: 4.9121. Min Range: -4.9121

Max Act: 3.5899. Min Act: -0.0001

Data Index: 1142670 (C4 (Web Text))

Max Activating Token Index: 421

Text #12

Max Range: 4.9121. Min Range: -4.9121

Max Act: 3.7382. Min Act: -0.0001

Data Index: 601148 (C4 (Web Text))

Max Activating Token Index: 957

Text #13

Max Range: 4.9121. Min Range: -4.9121

Max Act: 3.7496. Min Act: -0.0001

Data Index: 496116 (C4 (Web Text))

Max Activating Token Index: 77

Text #14

Max Range: 4.9121. Min Range: -4.9121

Max Act: 3.2361. Min Act: -0.0001

Data Index: 790140 (C4 (Web Text))

Max Activating Token Index: 552

Text #15

Max Range: 4.9121. Min Range: -4.9121

Max Act: 3.2542. Min Act: -0.0001

Data Index: 137194 (C4 (Web Text))

Max Activating Token Index: 714

Text #16

Max Range: 4.9121. Min Range: -4.9121

Max Act: 3.6739. Min Act: -0.0001

Data Index: 944025 (C4 (Web Text))

Max Activating Token Index: 903

Text #17

Max Range: 4.9121. Min Range: -4.9121

Max Act: 3.0608. Min Act: -0.0001

Data Index: 341267 (C4 (Web Text))

Max Activating Token Index: 153

Text #18

Max Range: 4.9121. Min Range: -4.9121

Max Act: 3.1245. Min Act: -0.0001

Data Index: 1317692 (C4 (Web Text))

Max Activating Token Index: 724

Text #19

Max Range: 4.9121. Min Range: -4.9121

Max Act: 3.1385. Min Act: -0.0001

Data Index: 1235468 (C4 (Web Text))

Max Activating Token Index: 696