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

Dataset: The Pile

Neuron 2114 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: 0.7705. Min Range: -0.7705

Max Act: 0.7072. Min Act: -0.0000

Data Index: 1088712 (The Pile)

Max Activating Token Index: 128

Text #1

Max Range: 0.7705. Min Range: -0.7705

Max Act: 0.7038. Min Act: 0.0000

Data Index: 1565745 (The Pile)

Max Activating Token Index: 162

Text #2

Max Range: 0.7705. Min Range: -0.7705

Max Act: 0.7705. Min Act: -0.0000

Data Index: 1874750 (The Pile)

Max Activating Token Index: 246

Text #3

Max Range: 0.7705. Min Range: -0.7705

Max Act: 0.7132. Min Act: -0.0000

Data Index: 281414 (The Pile)

Max Activating Token Index: 287

Text #4

Max Range: 0.7705. Min Range: -0.7705

Max Act: 0.6644. Min Act: -0.0000

Data Index: 1564711 (The Pile)

Max Activating Token Index: 249

Text #5

Max Range: 0.7705. Min Range: -0.7705

Max Act: 0.7057. Min Act: -0.0000

Data Index: 1579284 (The Pile)

Max Activating Token Index: 268

Text #6

Max Range: 0.7705. Min Range: -0.7705

Max Act: 0.6556. Min Act: -0.0000

Data Index: 1378348 (The Pile)

Max Activating Token Index: 511

Text #7

Max Range: 0.7705. Min Range: -0.7705

Max Act: 0.7509. Min Act: -0.0000

Data Index: 1460787 (The Pile)

Max Activating Token Index: 629

Text #8

Max Range: 0.7705. Min Range: -0.7705

Max Act: 0.6877. Min Act: -0.0000

Data Index: 633005 (The Pile)

Max Activating Token Index: 957

Text #9

Max Range: 0.7705. Min Range: -0.7705

Max Act: 0.5875. Min Act: -0.0000

Data Index: 1228333 (The Pile)

Max Activating Token Index: 874

Text #10

Max Range: 0.7705. Min Range: -0.7705

Max Act: 0.6416. Min Act: -0.0000

Data Index: 1104436 (The Pile)

Max Activating Token Index: 214

Text #11

Max Range: 0.7705. Min Range: -0.7705

Max Act: 0.6934. Min Act: -0.0000

Data Index: 1249730 (The Pile)

Max Activating Token Index: 446

Text #12

Max Range: 0.7705. Min Range: -0.7705

Max Act: 0.6293. Min Act: -0.0000

Data Index: 1699473 (The Pile)

Max Activating Token Index: 474

Text #13

Max Range: 0.7705. Min Range: -0.7705

Max Act: 0.6975. Min Act: -0.0000

Data Index: 1111126 (The Pile)

Max Activating Token Index: 159

Text #14

Max Range: 0.7705. Min Range: -0.7705

Max Act: 0.6185. Min Act: -0.0000

Data Index: 1142690 (The Pile)

Max Activating Token Index: 632

Text #15

Max Range: 0.7705. Min Range: -0.7705

Max Act: 0.5819. Min Act: -0.0000

Data Index: 1803749 (The Pile)

Max Activating Token Index: 860

Text #16

Max Range: 0.7705. Min Range: -0.7705

Max Act: 0.6154. Min Act: -0.0000

Data Index: 1047362 (The Pile)

Max Activating Token Index: 629

Text #17

Max Range: 0.7705. Min Range: -0.7705

Max Act: 0.6116. Min Act: -0.0000

Data Index: 1845194 (The Pile)

Max Activating Token Index: 719

Text #18

Max Range: 0.7705. Min Range: -0.7705

Max Act: 0.5809. Min Act: -0.0000

Data Index: 285118 (The Pile)

Max Activating Token Index: 800

Text #19

Max Range: 0.7705. Min Range: -0.7705

Max Act: 0.6715. Min Act: -0.0000

Data Index: 454069 (The Pile)

Max Activating Token Index: 746