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

Dataset: The Pile

Neuron 1703 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: 1.0633. Min Range: -1.0633

Max Act: 1.0633. Min Act: -0.0000

Data Index: 1610125 (The Pile)

Max Activating Token Index: 882

Text #1

Max Range: 1.0633. Min Range: -1.0633

Max Act: 0.9494. Min Act: -0.0000

Data Index: 1192271 (The Pile)

Max Activating Token Index: 369

Text #2

Max Range: 1.0633. Min Range: -1.0633

Max Act: 0.9464. Min Act: -0.0000

Data Index: 680067 (The Pile)

Max Activating Token Index: 780

Text #3

Max Range: 1.0633. Min Range: -1.0633

Max Act: 0.9864. Min Act: -0.0000

Data Index: 1824703 (The Pile)

Max Activating Token Index: 511

Text #4

Max Range: 1.0633. Min Range: -1.0633

Max Act: 0.7829. Min Act: -0.0000

Data Index: 1157278 (The Pile)

Max Activating Token Index: 657

Text #5

Max Range: 1.0633. Min Range: -1.0633

Max Act: 0.8488. Min Act: -0.0000

Data Index: 328176 (The Pile)

Max Activating Token Index: 335

Text #6

Max Range: 1.0633. Min Range: -1.0633

Max Act: 0.8175. Min Act: -0.0000

Data Index: 408857 (The Pile)

Max Activating Token Index: 568

Text #7

Max Range: 1.0633. Min Range: -1.0633

Max Act: 0.7965. Min Act: -0.0000

Data Index: 1919657 (The Pile)

Max Activating Token Index: 338

Text #8

Max Range: 1.0633. Min Range: -1.0633

Max Act: 0.8251. Min Act: -0.0000

Data Index: 1780271 (The Pile)

Max Activating Token Index: 547

Text #9

Max Range: 1.0633. Min Range: -1.0633

Max Act: 0.7064. Min Act: -0.0000

Data Index: 57394 (The Pile)

Max Activating Token Index: 785

Text #10

Max Range: 1.0633. Min Range: -1.0633

Max Act: 0.6705. Min Act: -0.0000

Data Index: 622844 (The Pile)

Max Activating Token Index: 613

Text #11

Max Range: 1.0633. Min Range: -1.0633

Max Act: 0.8131. Min Act: -0.0000

Data Index: 572618 (The Pile)

Max Activating Token Index: 777

Text #12

Max Range: 1.0633. Min Range: -1.0633

Max Act: 0.6170. Min Act: -0.0000

Data Index: 1143402 (The Pile)

Max Activating Token Index: 596

Text #13

Max Range: 1.0633. Min Range: -1.0633

Max Act: 0.7021. Min Act: -0.0000

Data Index: 1229442 (The Pile)

Max Activating Token Index: 935

Text #14

Max Range: 1.0633. Min Range: -1.0633

Max Act: 0.6819. Min Act: -0.0000

Data Index: 1548359 (The Pile)

Max Activating Token Index: 646

Text #15

Max Range: 1.0633. Min Range: -1.0633

Max Act: 0.6584. Min Act: -0.0000

Data Index: 675807 (The Pile)

Max Activating Token Index: 686

Text #16

Max Range: 1.0633. Min Range: -1.0633

Max Act: 0.6314. Min Act: -0.0000

Data Index: 131409 (The Pile)

Max Activating Token Index: 73

Text #17

Max Range: 1.0633. Min Range: -1.0633

Max Act: 0.6080. Min Act: -0.0000

Data Index: 1369543 (The Pile)

Max Activating Token Index: 824

Text #18

Max Range: 1.0633. Min Range: -1.0633

Max Act: 0.6110. Min Act: -0.0000

Data Index: 20283 (The Pile)

Max Activating Token Index: 354

Text #19

Max Range: 1.0633. Min Range: -1.0633

Max Act: 0.5897. Min Act: -0.0000

Data Index: 1024107 (The Pile)

Max Activating Token Index: 577