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

Dataset: The Pile

Neuron 4934 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: 1.2594. Min Range: -1.2594

Max Act: 1.2594. Min Act: -0.0000

Data Index: 677016 (The Pile)

Max Activating Token Index: 288

Text #1

Max Range: 1.2594. Min Range: -1.2594

Max Act: 0.8808. Min Act: -0.0000

Data Index: 1385449 (The Pile)

Max Activating Token Index: 212

Text #2

Max Range: 1.2594. Min Range: -1.2594

Max Act: 0.8576. Min Act: -0.0000

Data Index: 331141 (The Pile)

Max Activating Token Index: 773

Text #3

Max Range: 1.2594. Min Range: -1.2594

Max Act: 0.8714. Min Act: -0.0000

Data Index: 938038 (The Pile)

Max Activating Token Index: 583

Text #4

Max Range: 1.2594. Min Range: -1.2594

Max Act: 0.8636. Min Act: -0.0000

Data Index: 1939088 (The Pile)

Max Activating Token Index: 689

Text #5

Max Range: 1.2594. Min Range: -1.2594

Max Act: 0.8046. Min Act: -0.0000

Data Index: 1914593 (The Pile)

Max Activating Token Index: 555

Text #6

Max Range: 1.2594. Min Range: -1.2594

Max Act: 0.7955. Min Act: -0.0000

Data Index: 302586 (The Pile)

Max Activating Token Index: 197

Text #7

Max Range: 1.2594. Min Range: -1.2594

Max Act: 0.8047. Min Act: -0.0000

Data Index: 1367090 (The Pile)

Max Activating Token Index: 9

Text #8

Max Range: 1.2594. Min Range: -1.2594

Max Act: 0.6948. Min Act: -0.0000

Data Index: 231358 (The Pile)

Max Activating Token Index: 200

Text #9

Max Range: 1.2594. Min Range: -1.2594

Max Act: 0.7085. Min Act: -0.0000

Data Index: 1122250 (The Pile)

Max Activating Token Index: 439

Text #10

Max Range: 1.2594. Min Range: -1.2594

Max Act: 0.7340. Min Act: -0.0000

Data Index: 222641 (The Pile)

Max Activating Token Index: 428

Text #11

Max Range: 1.2594. Min Range: -1.2594

Max Act: 0.6844. Min Act: -0.0000

Data Index: 1035888 (The Pile)

Max Activating Token Index: 911

Text #12

Max Range: 1.2594. Min Range: -1.2594

Max Act: 0.7234. Min Act: -0.0000

Data Index: 734988 (The Pile)

Max Activating Token Index: 803

Text #13

Max Range: 1.2594. Min Range: -1.2594

Max Act: 0.7134. Min Act: -0.0000

Data Index: 1897395 (The Pile)

Max Activating Token Index: 67

Text #14

Max Range: 1.2594. Min Range: -1.2594

Max Act: 0.6707. Min Act: -0.0000

Data Index: 389616 (The Pile)

Max Activating Token Index: 499

Text #15

Max Range: 1.2594. Min Range: -1.2594

Max Act: 0.6438. Min Act: -0.0000

Data Index: 849098 (The Pile)

Max Activating Token Index: 793

Text #16

Max Range: 1.2594. Min Range: -1.2594

Max Act: 0.6844. Min Act: -0.0000

Data Index: 1152718 (The Pile)

Max Activating Token Index: 65

Text #17

Max Range: 1.2594. Min Range: -1.2594

Max Act: 0.6568. Min Act: -0.0000

Data Index: 1036529 (The Pile)

Max Activating Token Index: 376

Text #18

Max Range: 1.2594. Min Range: -1.2594

Max Act: 0.6325. Min Act: -0.0000

Data Index: 361827 (The Pile)

Max Activating Token Index: 137

Text #19

Max Range: 1.2594. Min Range: -1.2594

Max Act: 0.6591. Min Act: -0.0000

Data Index: 662446 (The Pile)

Max Activating Token Index: 62