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

Dataset: The Pile

Neuron 1570 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6236. Min Range: -0.6236

Max Act: 0.6236. Min Act: -0.0000

Data Index: 1174877 (The Pile)

Max Activating Token Index: 151

Text #1

Max Range: 0.6236. Min Range: -0.6236

Max Act: 0.5683. Min Act: -0.0000

Data Index: 1667524 (The Pile)

Max Activating Token Index: 563

Text #2

Max Range: 0.6236. Min Range: -0.6236

Max Act: 0.4806. Min Act: -0.0000

Data Index: 1900669 (The Pile)

Max Activating Token Index: 501

Text #3

Max Range: 0.6236. Min Range: -0.6236

Max Act: 0.4701. Min Act: -0.0000

Data Index: 684757 (The Pile)

Max Activating Token Index: 692

Text #4

Max Range: 0.6236. Min Range: -0.6236

Max Act: 0.4190. Min Act: -0.0000

Data Index: 1062958 (The Pile)

Max Activating Token Index: 310

Text #5

Max Range: 0.6236. Min Range: -0.6236

Max Act: 0.4263. Min Act: -0.0000

Data Index: 1206353 (The Pile)

Max Activating Token Index: 478

Text #6

Max Range: 0.6236. Min Range: -0.6236

Max Act: 0.3601. Min Act: -0.0000

Data Index: 1109800 (The Pile)

Max Activating Token Index: 455

Text #7

Max Range: 0.6236. Min Range: -0.6236

Max Act: 0.3397. Min Act: -0.0000

Data Index: 792000 (The Pile)

Max Activating Token Index: 248

Text #8

Max Range: 0.6236. Min Range: -0.6236

Max Act: 0.3591. Min Act: -0.0000

Data Index: 1563458 (The Pile)

Max Activating Token Index: 633

Text #9

Max Range: 0.6236. Min Range: -0.6236

Max Act: 0.3583. Min Act: -0.0000

Data Index: 1258643 (The Pile)

Max Activating Token Index: 443

Text #10

Max Range: 0.6236. Min Range: -0.6236

Max Act: 0.3267. Min Act: -0.0000

Data Index: 583340 (The Pile)

Max Activating Token Index: 736

Text #11

Max Range: 0.6236. Min Range: -0.6236

Max Act: 0.3286. Min Act: -0.0000

Data Index: 835214 (The Pile)

Max Activating Token Index: 845

Text #12

Max Range: 0.6236. Min Range: -0.6236

Max Act: 0.3136. Min Act: -0.0000

Data Index: 1505634 (The Pile)

Max Activating Token Index: 36

Text #13

Max Range: 0.6236. Min Range: -0.6236

Max Act: 0.3046. Min Act: -0.0000

Data Index: 1739012 (The Pile)

Max Activating Token Index: 800

Text #14

Max Range: 0.6236. Min Range: -0.6236

Max Act: 0.2827. Min Act: -0.0000

Data Index: 1869660 (The Pile)

Max Activating Token Index: 236

Text #15

Max Range: 0.6236. Min Range: -0.6236

Max Act: 0.2867. Min Act: -0.0000

Data Index: 1047934 (The Pile)

Max Activating Token Index: 460

Text #16

Max Range: 0.6236. Min Range: -0.6236

Max Act: 0.2845. Min Act: -0.0000

Data Index: 937992 (The Pile)

Max Activating Token Index: 533

Text #17

Max Range: 0.6236. Min Range: -0.6236

Max Act: 0.2709. Min Act: -0.0000

Data Index: 1351055 (The Pile)

Max Activating Token Index: 534

Text #18

Max Range: 0.6236. Min Range: -0.6236

Max Act: 0.2721. Min Act: -0.0000

Data Index: 133327 (The Pile)

Max Activating Token Index: 309

Text #19

Max Range: 0.6236. Min Range: -0.6236

Max Act: 0.2688. Min Act: -0.0000

Data Index: 1579763 (The Pile)

Max Activating Token Index: 684