Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 240 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.7495. Min Range: -0.7495

Max Act: 0.7495. Min Act: -0.0000

Data Index: 740969 (The Pile)

Max Activating Token Index: 207

Text #1

Max Range: 0.7495. Min Range: -0.7495

Max Act: 0.7077. Min Act: -0.0000

Data Index: 747594 (The Pile)

Max Activating Token Index: 565

Text #2

Max Range: 0.7495. Min Range: -0.7495

Max Act: 0.6018. Min Act: -0.0000

Data Index: 1609843 (The Pile)

Max Activating Token Index: 938

Text #3

Max Range: 0.7495. Min Range: -0.7495

Max Act: 0.6015. Min Act: -0.0000

Data Index: 1504789 (The Pile)

Max Activating Token Index: 428

Text #4

Max Range: 0.7495. Min Range: -0.7495

Max Act: 0.5523. Min Act: -0.0000

Data Index: 1739332 (The Pile)

Max Activating Token Index: 797

Text #5

Max Range: 0.7495. Min Range: -0.7495

Max Act: 0.5852. Min Act: -0.0000

Data Index: 514292 (The Pile)

Max Activating Token Index: 195

Text #6

Max Range: 0.7495. Min Range: -0.7495

Max Act: 0.5512. Min Act: -0.0000

Data Index: 1052463 (The Pile)

Max Activating Token Index: 106

Text #7

Max Range: 0.7495. Min Range: -0.7495

Max Act: 0.5075. Min Act: -0.0000

Data Index: 1650386 (The Pile)

Max Activating Token Index: 557

Text #8

Max Range: 0.7495. Min Range: -0.7495

Max Act: 0.5201. Min Act: -0.0000

Data Index: 253094 (The Pile)

Max Activating Token Index: 366

Text #9

Max Range: 0.7495. Min Range: -0.7495

Max Act: 0.5351. Min Act: -0.0000

Data Index: 1977982 (The Pile)

Max Activating Token Index: 296

Text #10

Max Range: 0.7495. Min Range: -0.7495

Max Act: 0.5290. Min Act: -0.0000

Data Index: 174911 (The Pile)

Max Activating Token Index: 384

Text #11

Max Range: 0.7495. Min Range: -0.7495

Max Act: 0.5005. Min Act: -0.0000

Data Index: 1949245 (The Pile)

Max Activating Token Index: 85

Text #12

Max Range: 0.7495. Min Range: -0.7495

Max Act: 0.4798. Min Act: -0.0000

Data Index: 1651417 (The Pile)

Max Activating Token Index: 980

Text #13

Max Range: 0.7495. Min Range: -0.7495

Max Act: 0.4980. Min Act: -0.0000

Data Index: 1220904 (The Pile)

Max Activating Token Index: 362

Text #14

Max Range: 0.7495. Min Range: -0.7495

Max Act: 0.5099. Min Act: -0.0000

Data Index: 1800717 (The Pile)

Max Activating Token Index: 990

Text #15

Max Range: 0.7495. Min Range: -0.7495

Max Act: 0.5079. Min Act: -0.0000

Data Index: 536718 (The Pile)

Max Activating Token Index: 425

Text #16

Max Range: 0.7495. Min Range: -0.7495

Max Act: 0.5067. Min Act: -0.0000

Data Index: 196537 (The Pile)

Max Activating Token Index: 78

Text #17

Max Range: 0.7495. Min Range: -0.7495

Max Act: 0.4713. Min Act: -0.0000

Data Index: 1332656 (The Pile)

Max Activating Token Index: 636

Text #18

Max Range: 0.7495. Min Range: -0.7495

Max Act: 0.4062. Min Act: -0.0000

Data Index: 376942 (The Pile)

Max Activating Token Index: 70

Text #19

Max Range: 0.7495. Min Range: -0.7495

Max Act: 0.4525. Min Act: -0.0000

Data Index: 413333 (The Pile)

Max Activating Token Index: 810