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

Dataset: The Pile

Neuron 4124 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: 0.3157. Min Range: -0.3157

Max Act: 0.3115. Min Act: -0.0000

Data Index: 371376 (The Pile)

Max Activating Token Index: 827

Text #1

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.3157. Min Act: -0.0000

Data Index: 1652683 (The Pile)

Max Activating Token Index: 741

Text #2

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.3138. Min Act: -0.0000

Data Index: 1550517 (The Pile)

Max Activating Token Index: 876

Text #3

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2667. Min Act: -0.0000

Data Index: 1973538 (The Pile)

Max Activating Token Index: 872

Text #4

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2621. Min Act: -0.0000

Data Index: 1331826 (The Pile)

Max Activating Token Index: 744

Text #5

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2666. Min Act: -0.0000

Data Index: 25712 (The Pile)

Max Activating Token Index: 890

Text #6

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2650. Min Act: -0.0000

Data Index: 514069 (The Pile)

Max Activating Token Index: 695

Text #7

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2577. Min Act: -0.0000

Data Index: 724721 (The Pile)

Max Activating Token Index: 446

Text #8

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2604. Min Act: -0.0000

Data Index: 1307847 (The Pile)

Max Activating Token Index: 567

Text #9

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2485. Min Act: -0.0000

Data Index: 1726331 (The Pile)

Max Activating Token Index: 865

Text #10

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2610. Min Act: -0.0000

Data Index: 1312352 (The Pile)

Max Activating Token Index: 969

Text #11

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2371. Min Act: -0.0000

Data Index: 1161467 (The Pile)

Max Activating Token Index: 477

Text #12

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2492. Min Act: -0.0000

Data Index: 102939 (The Pile)

Max Activating Token Index: 702

Text #13

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2539. Min Act: -0.0000

Data Index: 968702 (The Pile)

Max Activating Token Index: 876

Text #14

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2452. Min Act: -0.0000

Data Index: 1197300 (The Pile)

Max Activating Token Index: 761

Text #15

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2596. Min Act: -0.0000

Data Index: 210126 (The Pile)

Max Activating Token Index: 984

Text #16

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2357. Min Act: -0.0000

Data Index: 1620559 (The Pile)

Max Activating Token Index: 354

Text #17

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2420. Min Act: -0.0000

Data Index: 101345 (The Pile)

Max Activating Token Index: 355

Text #18

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2261. Min Act: -0.0000

Data Index: 1653747 (The Pile)

Max Activating Token Index: 643

Text #19

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2250. Min Act: -0.0000

Data Index: 872966 (The Pile)

Max Activating Token Index: 369