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

Dataset: The Pile

Neuron 974 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7902. Min Range: -1.7902

Max Act: 1.7902. Min Act: -0.0000

Data Index: 634618 (The Pile)

Max Activating Token Index: 585

Text #1

Max Range: 1.7902. Min Range: -1.7902

Max Act: 1.6635. Min Act: -0.0000

Data Index: 1746130 (The Pile)

Max Activating Token Index: 290

Text #2

Max Range: 1.7902. Min Range: -1.7902

Max Act: 1.5911. Min Act: -0.0000

Data Index: 839343 (The Pile)

Max Activating Token Index: 550

Text #3

Max Range: 1.7902. Min Range: -1.7902

Max Act: 1.5217. Min Act: -0.0000

Data Index: 905277 (The Pile)

Max Activating Token Index: 197

Text #4

Max Range: 1.7902. Min Range: -1.7902

Max Act: 1.6012. Min Act: -0.0000

Data Index: 498318 (The Pile)

Max Activating Token Index: 406

Text #5

Max Range: 1.7902. Min Range: -1.7902

Max Act: 1.5604. Min Act: -0.0001

Data Index: 1534995 (The Pile)

Max Activating Token Index: 412

Text #6

Max Range: 1.7902. Min Range: -1.7902

Max Act: 1.5533. Min Act: -0.0000

Data Index: 1147930 (The Pile)

Max Activating Token Index: 730

Text #7

Max Range: 1.7902. Min Range: -1.7902

Max Act: 1.5375. Min Act: -0.0000

Data Index: 79850 (The Pile)

Max Activating Token Index: 212

Text #8

Max Range: 1.7902. Min Range: -1.7902

Max Act: 1.6339. Min Act: -0.0000

Data Index: 1781006 (The Pile)

Max Activating Token Index: 827

Text #9

Max Range: 1.7902. Min Range: -1.7902

Max Act: 1.5115. Min Act: -0.0000

Data Index: 1878489 (The Pile)

Max Activating Token Index: 483

Text #10

Max Range: 1.7902. Min Range: -1.7902

Max Act: 1.4132. Min Act: -0.0000

Data Index: 1565228 (The Pile)

Max Activating Token Index: 857

Text #11

Max Range: 1.7902. Min Range: -1.7902

Max Act: 1.4085. Min Act: -0.0000

Data Index: 1363098 (The Pile)

Max Activating Token Index: 443

Text #12

Max Range: 1.7902. Min Range: -1.7902

Max Act: 1.4028. Min Act: -0.0000

Data Index: 1623594 (The Pile)

Max Activating Token Index: 307

Text #13

Max Range: 1.7902. Min Range: -1.7902

Max Act: 1.4722. Min Act: -0.0000

Data Index: 1515732 (The Pile)

Max Activating Token Index: 49

Text #14

Max Range: 1.7902. Min Range: -1.7902

Max Act: 1.4676. Min Act: -0.0000

Data Index: 350329 (The Pile)

Max Activating Token Index: 51

Text #15

Max Range: 1.7902. Min Range: -1.7902

Max Act: 1.4683. Min Act: -0.0000

Data Index: 855687 (The Pile)

Max Activating Token Index: 723

Text #16

Max Range: 1.7902. Min Range: -1.7902

Max Act: 1.4641. Min Act: -0.0000

Data Index: 1236380 (The Pile)

Max Activating Token Index: 336

Text #17

Max Range: 1.7902. Min Range: -1.7902

Max Act: 1.5485. Min Act: -0.0000

Data Index: 313256 (The Pile)

Max Activating Token Index: 231

Text #18

Max Range: 1.7902. Min Range: -1.7902

Max Act: 1.4400. Min Act: -0.0000

Data Index: 1860795 (The Pile)

Max Activating Token Index: 829

Text #19

Max Range: 1.7902. Min Range: -1.7902

Max Act: 1.4261. Min Act: -0.0000

Data Index: 1783411 (The Pile)

Max Activating Token Index: 487