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

Dataset: The Pile

Neuron 3233 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8406. Min Range: -0.8406

Max Act: 0.8406. Min Act: -0.0000

Data Index: 233717 (The Pile)

Max Activating Token Index: 669

Text #1

Max Range: 0.8406. Min Range: -0.8406

Max Act: 0.7272. Min Act: -0.0000

Data Index: 212540 (The Pile)

Max Activating Token Index: 866

Text #2

Max Range: 0.8406. Min Range: -0.8406

Max Act: 0.7276. Min Act: -0.0000

Data Index: 1547406 (The Pile)

Max Activating Token Index: 190

Text #3

Max Range: 0.8406. Min Range: -0.8406

Max Act: 0.6947. Min Act: -0.0000

Data Index: 702008 (The Pile)

Max Activating Token Index: 57

Text #4

Max Range: 0.8406. Min Range: -0.8406

Max Act: 0.7159. Min Act: -0.0000

Data Index: 181926 (The Pile)

Max Activating Token Index: 968

Text #5

Max Range: 0.8406. Min Range: -0.8406

Max Act: 0.5808. Min Act: -0.0000

Data Index: 1722103 (The Pile)

Max Activating Token Index: 156

Text #6

Max Range: 0.8406. Min Range: -0.8406

Max Act: 0.6958. Min Act: -0.0000

Data Index: 328780 (The Pile)

Max Activating Token Index: 673

Text #7

Max Range: 0.8406. Min Range: -0.8406

Max Act: 0.6486. Min Act: -0.0000

Data Index: 745853 (The Pile)

Max Activating Token Index: 815

Text #8

Max Range: 0.8406. Min Range: -0.8406

Max Act: 0.7244. Min Act: -0.0000

Data Index: 493745 (The Pile)

Max Activating Token Index: 792

Text #9

Max Range: 0.8406. Min Range: -0.8406

Max Act: 0.6501. Min Act: -0.0000

Data Index: 660972 (The Pile)

Max Activating Token Index: 646

Text #10

Max Range: 0.8406. Min Range: -0.8406

Max Act: 0.6535. Min Act: -0.0000

Data Index: 471647 (The Pile)

Max Activating Token Index: 1005

Text #11

Max Range: 0.8406. Min Range: -0.8406

Max Act: 0.7190. Min Act: -0.0000

Data Index: 512775 (The Pile)

Max Activating Token Index: 322

Text #12

Max Range: 0.8406. Min Range: -0.8406

Max Act: 0.6648. Min Act: -0.0000

Data Index: 916980 (The Pile)

Max Activating Token Index: 497

Text #13

Max Range: 0.8406. Min Range: -0.8406

Max Act: 0.6784. Min Act: -0.0000

Data Index: 274932 (The Pile)

Max Activating Token Index: 487

Text #14

Max Range: 0.8406. Min Range: -0.8406

Max Act: 0.5938. Min Act: -0.0000

Data Index: 1794927 (The Pile)

Max Activating Token Index: 300

Text #15

Max Range: 0.8406. Min Range: -0.8406

Max Act: 0.5679. Min Act: -0.0000

Data Index: 1515238 (The Pile)

Max Activating Token Index: 997

Text #16

Max Range: 0.8406. Min Range: -0.8406

Max Act: 0.5533. Min Act: -0.0000

Data Index: 1875501 (The Pile)

Max Activating Token Index: 641

Text #17

Max Range: 0.8406. Min Range: -0.8406

Max Act: 0.5776. Min Act: -0.0000

Data Index: 662148 (The Pile)

Max Activating Token Index: 633

Text #18

Max Range: 0.8406. Min Range: -0.8406

Max Act: 0.5971. Min Act: -0.0000

Data Index: 1221792 (The Pile)

Max Activating Token Index: 486

Text #19

Max Range: 0.8406. Min Range: -0.8406

Max Act: 0.5656. Min Act: -0.0000

Data Index: 520867 (The Pile)

Max Activating Token Index: 385