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

Dataset: The Pile

Neuron 4529 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8192. Min Range: -1.8192

Max Act: 1.7423. Min Act: -0.0000

Data Index: 840419 (The Pile)

Max Activating Token Index: 940

Text #1

Max Range: 1.8192. Min Range: -1.8192

Max Act: 1.8192. Min Act: -0.0000

Data Index: 1469166 (The Pile)

Max Activating Token Index: 1008

Text #2

Max Range: 1.8192. Min Range: -1.8192

Max Act: 1.7305. Min Act: -0.0000

Data Index: 1666807 (The Pile)

Max Activating Token Index: 878

Text #3

Max Range: 1.8192. Min Range: -1.8192

Max Act: 1.7081. Min Act: -0.0000

Data Index: 1957146 (The Pile)

Max Activating Token Index: 416

Text #4

Max Range: 1.8192. Min Range: -1.8192

Max Act: 1.8061. Min Act: -0.0000

Data Index: 701843 (The Pile)

Max Activating Token Index: 970

Text #5

Max Range: 1.8192. Min Range: -1.8192

Max Act: 1.6855. Min Act: -0.0000

Data Index: 322550 (The Pile)

Max Activating Token Index: 734

Text #6

Max Range: 1.8192. Min Range: -1.8192

Max Act: 1.5684. Min Act: -0.0000

Data Index: 1155221 (The Pile)

Max Activating Token Index: 971

Text #7

Max Range: 1.8192. Min Range: -1.8192

Max Act: 1.6611. Min Act: -0.0000

Data Index: 858600 (The Pile)

Max Activating Token Index: 515

Text #8

Max Range: 1.8192. Min Range: -1.8192

Max Act: 1.7533. Min Act: -0.0000

Data Index: 892312 (The Pile)

Max Activating Token Index: 958

Text #9

Max Range: 1.8192. Min Range: -1.8192

Max Act: 1.6571. Min Act: -0.0000

Data Index: 1185447 (The Pile)

Max Activating Token Index: 519

Text #10

Max Range: 1.8192. Min Range: -1.8192

Max Act: 1.7047. Min Act: -0.0000

Data Index: 1823342 (The Pile)

Max Activating Token Index: 778

Text #11

Max Range: 1.8192. Min Range: -1.8192

Max Act: 1.6038. Min Act: -0.0000

Data Index: 766973 (The Pile)

Max Activating Token Index: 274

Text #12

Max Range: 1.8192. Min Range: -1.8192

Max Act: 1.5211. Min Act: -0.0000

Data Index: 340898 (The Pile)

Max Activating Token Index: 626

Text #13

Max Range: 1.8192. Min Range: -1.8192

Max Act: 1.7669. Min Act: -0.0000

Data Index: 300926 (The Pile)

Max Activating Token Index: 945

Text #14

Max Range: 1.8192. Min Range: -1.8192

Max Act: 1.5429. Min Act: -0.0000

Data Index: 1047995 (The Pile)

Max Activating Token Index: 751

Text #15

Max Range: 1.8192. Min Range: -1.8192

Max Act: 1.3416. Min Act: -0.0000

Data Index: 1066529 (The Pile)

Max Activating Token Index: 208

Text #16

Max Range: 1.8192. Min Range: -1.8192

Max Act: 1.4832. Min Act: -0.0000

Data Index: 1848886 (The Pile)

Max Activating Token Index: 1007

Text #17

Max Range: 1.8192. Min Range: -1.8192

Max Act: 1.5797. Min Act: -0.0000

Data Index: 180990 (The Pile)

Max Activating Token Index: 508

Text #18

Max Range: 1.8192. Min Range: -1.8192

Max Act: 1.5641. Min Act: -0.0000

Data Index: 1743667 (The Pile)

Max Activating Token Index: 800

Text #19

Max Range: 1.8192. Min Range: -1.8192

Max Act: 1.4782. Min Act: -0.0000

Data Index: 23434 (The Pile)

Max Activating Token Index: 502