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

Dataset: The Pile

Neuron 1664 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7477. Min Range: -1.7477

Max Act: 1.7477. Min Act: -0.0000

Data Index: 530467 (The Pile)

Max Activating Token Index: 909

Text #1

Max Range: 1.7477. Min Range: -1.7477

Max Act: 1.1153. Min Act: -0.0000

Data Index: 1483468 (The Pile)

Max Activating Token Index: 435

Text #2

Max Range: 1.7477. Min Range: -1.7477

Max Act: 1.0323. Min Act: -0.0000

Data Index: 1217826 (The Pile)

Max Activating Token Index: 840

Text #3

Max Range: 1.7477. Min Range: -1.7477

Max Act: 1.0495. Min Act: -0.0000

Data Index: 1162375 (The Pile)

Max Activating Token Index: 715

Text #4

Max Range: 1.7477. Min Range: -1.7477

Max Act: 1.1088. Min Act: -0.0000

Data Index: 637355 (The Pile)

Max Activating Token Index: 905

Text #5

Max Range: 1.7477. Min Range: -1.7477

Max Act: 0.9986. Min Act: -0.0000

Data Index: 1440671 (The Pile)

Max Activating Token Index: 85

Text #6

Max Range: 1.7477. Min Range: -1.7477

Max Act: 0.9872. Min Act: -0.0000

Data Index: 1067163 (The Pile)

Max Activating Token Index: 250

Text #7

Max Range: 1.7477. Min Range: -1.7477

Max Act: 0.8581. Min Act: -0.0000

Data Index: 1796140 (The Pile)

Max Activating Token Index: 847

Text #8

Max Range: 1.7477. Min Range: -1.7477

Max Act: 1.0412. Min Act: -0.0000

Data Index: 469271 (The Pile)

Max Activating Token Index: 893

Text #9

Max Range: 1.7477. Min Range: -1.7477

Max Act: 0.8782. Min Act: -0.0000

Data Index: 1139479 (The Pile)

Max Activating Token Index: 144

Text #10

Max Range: 1.7477. Min Range: -1.7477

Max Act: 0.8238. Min Act: -0.0001

Data Index: 1963030 (The Pile)

Max Activating Token Index: 936

Text #11

Max Range: 1.7477. Min Range: -1.7477

Max Act: 0.8487. Min Act: -0.0000

Data Index: 499732 (The Pile)

Max Activating Token Index: 498

Text #12

Max Range: 1.7477. Min Range: -1.7477

Max Act: 0.8569. Min Act: -0.0000

Data Index: 132603 (The Pile)

Max Activating Token Index: 694

Text #13

Max Range: 1.7477. Min Range: -1.7477

Max Act: 0.7492. Min Act: -0.0000

Data Index: 371606 (The Pile)

Max Activating Token Index: 937

Text #14

Max Range: 1.7477. Min Range: -1.7477

Max Act: 0.9321. Min Act: -0.0000

Data Index: 1037732 (The Pile)

Max Activating Token Index: 274

Text #15

Max Range: 1.7477. Min Range: -1.7477

Max Act: 0.8960. Min Act: -0.0000

Data Index: 751901 (The Pile)

Max Activating Token Index: 456

Text #16

Max Range: 1.7477. Min Range: -1.7477

Max Act: 0.8976. Min Act: -0.0000

Data Index: 10367 (The Pile)

Max Activating Token Index: 134

Text #17

Max Range: 1.7477. Min Range: -1.7477

Max Act: 0.8987. Min Act: -0.0000

Data Index: 788435 (The Pile)

Max Activating Token Index: 456

Text #18

Max Range: 1.7477. Min Range: -1.7477

Max Act: 0.7813. Min Act: -0.0000

Data Index: 804571 (The Pile)

Max Activating Token Index: 931

Text #19

Max Range: 1.7477. Min Range: -1.7477

Max Act: 0.7846. Min Act: -0.0000

Data Index: 1797028 (The Pile)

Max Activating Token Index: 579