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

Dataset: The Pile

Neuron 2551 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6611. Min Range: -0.6611

Max Act: 0.6611. Min Act: -0.0000

Data Index: 688764 (The Pile)

Max Activating Token Index: 730

Text #1

Max Range: 0.6611. Min Range: -0.6611

Max Act: 0.5594. Min Act: -0.0000

Data Index: 717516 (The Pile)

Max Activating Token Index: 539

Text #2

Max Range: 0.6611. Min Range: -0.6611

Max Act: 0.5489. Min Act: -0.0000

Data Index: 1549870 (The Pile)

Max Activating Token Index: 299

Text #3

Max Range: 0.6611. Min Range: -0.6611

Max Act: 0.5232. Min Act: -0.0000

Data Index: 1250494 (The Pile)

Max Activating Token Index: 129

Text #4

Max Range: 0.6611. Min Range: -0.6611

Max Act: 0.5080. Min Act: -0.0000

Data Index: 1755863 (The Pile)

Max Activating Token Index: 983

Text #5

Max Range: 0.6611. Min Range: -0.6611

Max Act: 0.4543. Min Act: -0.0000

Data Index: 646676 (The Pile)

Max Activating Token Index: 650

Text #6

Max Range: 0.6611. Min Range: -0.6611

Max Act: 0.4682. Min Act: -0.0000

Data Index: 1890722 (The Pile)

Max Activating Token Index: 95

Text #7

Max Range: 0.6611. Min Range: -0.6611

Max Act: 0.4635. Min Act: -0.0000

Data Index: 1223190 (The Pile)

Max Activating Token Index: 33

Text #8

Max Range: 0.6611. Min Range: -0.6611

Max Act: 0.4606. Min Act: -0.0000

Data Index: 1835354 (The Pile)

Max Activating Token Index: 137

Text #9

Max Range: 0.6611. Min Range: -0.6611

Max Act: 0.4586. Min Act: -0.0000

Data Index: 1996927 (The Pile)

Max Activating Token Index: 214

Text #10

Max Range: 0.6611. Min Range: -0.6611

Max Act: 0.4724. Min Act: -0.0000

Data Index: 810212 (The Pile)

Max Activating Token Index: 457

Text #11

Max Range: 0.6611. Min Range: -0.6611

Max Act: 0.4685. Min Act: -0.0000

Data Index: 682718 (The Pile)

Max Activating Token Index: 564

Text #12

Max Range: 0.6611. Min Range: -0.6611

Max Act: 0.4506. Min Act: -0.0000

Data Index: 1321520 (The Pile)

Max Activating Token Index: 428

Text #13

Max Range: 0.6611. Min Range: -0.6611

Max Act: 0.4174. Min Act: -0.0000

Data Index: 1320991 (The Pile)

Max Activating Token Index: 883

Text #14

Max Range: 0.6611. Min Range: -0.6611

Max Act: 0.4299. Min Act: -0.0000

Data Index: 939772 (The Pile)

Max Activating Token Index: 167

Text #15

Max Range: 0.6611. Min Range: -0.6611

Max Act: 0.4624. Min Act: -0.0000

Data Index: 446195 (The Pile)

Max Activating Token Index: 807

Text #16

Max Range: 0.6611. Min Range: -0.6611

Max Act: 0.4315. Min Act: -0.0000

Data Index: 1805827 (The Pile)

Max Activating Token Index: 650

Text #17

Max Range: 0.6611. Min Range: -0.6611

Max Act: 0.4596. Min Act: -0.0000

Data Index: 1860129 (The Pile)

Max Activating Token Index: 655

Text #18

Max Range: 0.6611. Min Range: -0.6611

Max Act: 0.4109. Min Act: -0.0000

Data Index: 457770 (The Pile)

Max Activating Token Index: 311

Text #19

Max Range: 0.6611. Min Range: -0.6611

Max Act: 0.4260. Min Act: -0.0000

Data Index: 1473377 (The Pile)

Max Activating Token Index: 608