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

Dataset: The Pile

Neuron 3875 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9968. Min Range: -0.9968

Max Act: 0.9968. Min Act: -0.0000

Data Index: 894068 (The Pile)

Max Activating Token Index: 739

Text #1

Max Range: 0.9968. Min Range: -0.9968

Max Act: 0.9607. Min Act: -0.0000

Data Index: 421218 (The Pile)

Max Activating Token Index: 568

Text #2

Max Range: 0.9968. Min Range: -0.9968

Max Act: 0.9855. Min Act: -0.0000

Data Index: 938033 (The Pile)

Max Activating Token Index: 637

Text #3

Max Range: 0.9968. Min Range: -0.9968

Max Act: 0.8834. Min Act: -0.0000

Data Index: 807490 (The Pile)

Max Activating Token Index: 782

Text #4

Max Range: 0.9968. Min Range: -0.9968

Max Act: 0.9397. Min Act: -0.0000

Data Index: 1966846 (The Pile)

Max Activating Token Index: 459

Text #5

Max Range: 0.9968. Min Range: -0.9968

Max Act: 0.9073. Min Act: -0.0000

Data Index: 990819 (The Pile)

Max Activating Token Index: 500

Text #6

Max Range: 0.9968. Min Range: -0.9968

Max Act: 0.9396. Min Act: -0.0000

Data Index: 1220878 (The Pile)

Max Activating Token Index: 921

Text #7

Max Range: 0.9968. Min Range: -0.9968

Max Act: 0.9155. Min Act: -0.0000

Data Index: 1036141 (The Pile)

Max Activating Token Index: 743

Text #8

Max Range: 0.9968. Min Range: -0.9968

Max Act: 0.9234. Min Act: -0.0000

Data Index: 758827 (The Pile)

Max Activating Token Index: 951

Text #9

Max Range: 0.9968. Min Range: -0.9968

Max Act: 0.8539. Min Act: -0.0000

Data Index: 1718360 (The Pile)

Max Activating Token Index: 71

Text #10

Max Range: 0.9968. Min Range: -0.9968

Max Act: 0.8977. Min Act: -0.0000

Data Index: 1713580 (The Pile)

Max Activating Token Index: 738

Text #11

Max Range: 0.9968. Min Range: -0.9968

Max Act: 0.7853. Min Act: -0.0000

Data Index: 1385455 (The Pile)

Max Activating Token Index: 652

Text #12

Max Range: 0.9968. Min Range: -0.9968

Max Act: 0.7207. Min Act: -0.0000

Data Index: 527032 (The Pile)

Max Activating Token Index: 945

Text #13

Max Range: 0.9968. Min Range: -0.9968

Max Act: 0.7594. Min Act: -0.0000

Data Index: 508789 (The Pile)

Max Activating Token Index: 677

Text #14

Max Range: 0.9968. Min Range: -0.9968

Max Act: 0.7979. Min Act: -0.0000

Data Index: 353431 (The Pile)

Max Activating Token Index: 24

Text #15

Max Range: 0.9968. Min Range: -0.9968

Max Act: 0.8418. Min Act: -0.0000

Data Index: 1168756 (The Pile)

Max Activating Token Index: 159

Text #16

Max Range: 0.9968. Min Range: -0.9968

Max Act: 0.7944. Min Act: -0.0000

Data Index: 547324 (The Pile)

Max Activating Token Index: 546

Text #17

Max Range: 0.9968. Min Range: -0.9968

Max Act: 0.8419. Min Act: -0.0000

Data Index: 318624 (The Pile)

Max Activating Token Index: 497

Text #18

Max Range: 0.9968. Min Range: -0.9968

Max Act: 0.7941. Min Act: -0.0000

Data Index: 1810408 (The Pile)

Max Activating Token Index: 671

Text #19

Max Range: 0.9968. Min Range: -0.9968

Max Act: 0.8062. Min Act: -0.0000

Data Index: 1617168 (The Pile)

Max Activating Token Index: 104