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

Dataset: The Pile

Neuron 3708 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8668. Min Range: -0.8668

Max Act: 0.8386. Min Act: -0.0000

Data Index: 950353 (The Pile)

Max Activating Token Index: 698

Text #1

Max Range: 0.8668. Min Range: -0.8668

Max Act: 0.8668. Min Act: -0.0000

Data Index: 405590 (The Pile)

Max Activating Token Index: 404

Text #2

Max Range: 0.8668. Min Range: -0.8668

Max Act: 0.7608. Min Act: -0.0000

Data Index: 1212464 (The Pile)

Max Activating Token Index: 199

Text #3

Max Range: 0.8668. Min Range: -0.8668

Max Act: 0.5721. Min Act: -0.0000

Data Index: 1110236 (The Pile)

Max Activating Token Index: 305

Text #4

Max Range: 0.8668. Min Range: -0.8668

Max Act: 0.5912. Min Act: -0.0000

Data Index: 1311654 (The Pile)

Max Activating Token Index: 57

Text #5

Max Range: 0.8668. Min Range: -0.8668

Max Act: 0.5532. Min Act: -0.0000

Data Index: 1374144 (The Pile)

Max Activating Token Index: 611

Text #6

Max Range: 0.8668. Min Range: -0.8668

Max Act: 0.5960. Min Act: -0.0000

Data Index: 1242762 (The Pile)

Max Activating Token Index: 188

Text #7

Max Range: 0.8668. Min Range: -0.8668

Max Act: 0.5907. Min Act: -0.0000

Data Index: 1521228 (The Pile)

Max Activating Token Index: 31

Text #8

Max Range: 0.8668. Min Range: -0.8668

Max Act: 0.5776. Min Act: -0.0000

Data Index: 1615619 (The Pile)

Max Activating Token Index: 602

Text #9

Max Range: 0.8668. Min Range: -0.8668

Max Act: 0.5434. Min Act: -0.0000

Data Index: 1048351 (The Pile)

Max Activating Token Index: 297

Text #10

Max Range: 0.8668. Min Range: -0.8668

Max Act: 0.6166. Min Act: -0.0000

Data Index: 785739 (The Pile)

Max Activating Token Index: 412

Text #11

Max Range: 0.8668. Min Range: -0.8668

Max Act: 0.4817. Min Act: -0.0000

Data Index: 933317 (The Pile)

Max Activating Token Index: 346

Text #12

Max Range: 0.8668. Min Range: -0.8668

Max Act: 0.5320. Min Act: -0.0000

Data Index: 1389152 (The Pile)

Max Activating Token Index: 726

Text #13

Max Range: 0.8668. Min Range: -0.8668

Max Act: 0.4336. Min Act: -0.0000

Data Index: 271543 (The Pile)

Max Activating Token Index: 971

Text #14

Max Range: 0.8668. Min Range: -0.8668

Max Act: 0.5116. Min Act: -0.0000

Data Index: 693829 (The Pile)

Max Activating Token Index: 173

Text #15

Max Range: 0.8668. Min Range: -0.8668

Max Act: 0.4668. Min Act: -0.0000

Data Index: 362571 (The Pile)

Max Activating Token Index: 45

Text #16

Max Range: 0.8668. Min Range: -0.8668

Max Act: 0.4894. Min Act: -0.0000

Data Index: 168931 (The Pile)

Max Activating Token Index: 760

Text #17

Max Range: 0.8668. Min Range: -0.8668

Max Act: 0.5131. Min Act: -0.0000

Data Index: 1454804 (The Pile)

Max Activating Token Index: 208

Text #18

Max Range: 0.8668. Min Range: -0.8668

Max Act: 0.4663. Min Act: -0.0000

Data Index: 618314 (The Pile)

Max Activating Token Index: 966

Text #19

Max Range: 0.8668. Min Range: -0.8668

Max Act: 0.5093. Min Act: -0.0000

Data Index: 1000987 (The Pile)

Max Activating Token Index: 97