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

Dataset: The Pile

Neuron 3760 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5881. Min Range: -0.5881

Max Act: 0.5881. Min Act: -0.0000

Data Index: 840614 (The Pile)

Max Activating Token Index: 7

Text #1

Max Range: 0.5881. Min Range: -0.5881

Max Act: 0.5135. Min Act: -0.0000

Data Index: 114416 (The Pile)

Max Activating Token Index: 717

Text #2

Max Range: 0.5881. Min Range: -0.5881

Max Act: 0.5287. Min Act: -0.0000

Data Index: 1540991 (The Pile)

Max Activating Token Index: 537

Text #3

Max Range: 0.5881. Min Range: -0.5881

Max Act: 0.5121. Min Act: -0.0000

Data Index: 986446 (The Pile)

Max Activating Token Index: 287

Text #4

Max Range: 0.5881. Min Range: -0.5881

Max Act: 0.5018. Min Act: -0.0000

Data Index: 1124068 (The Pile)

Max Activating Token Index: 293

Text #5

Max Range: 0.5881. Min Range: -0.5881

Max Act: 0.4844. Min Act: -0.0000

Data Index: 1570579 (The Pile)

Max Activating Token Index: 93

Text #6

Max Range: 0.5881. Min Range: -0.5881

Max Act: 0.4567. Min Act: -0.0000

Data Index: 1730049 (The Pile)

Max Activating Token Index: 941

Text #7

Max Range: 0.5881. Min Range: -0.5881

Max Act: 0.4313. Min Act: -0.0000

Data Index: 1145124 (The Pile)

Max Activating Token Index: 546

Text #8

Max Range: 0.5881. Min Range: -0.5881

Max Act: 0.4352. Min Act: -0.0000

Data Index: 1058211 (The Pile)

Max Activating Token Index: 322

Text #9

Max Range: 0.5881. Min Range: -0.5881

Max Act: 0.3914. Min Act: -0.0000

Data Index: 1227955 (The Pile)

Max Activating Token Index: 743

Text #10

Max Range: 0.5881. Min Range: -0.5881

Max Act: 0.4194. Min Act: -0.0000

Data Index: 1462101 (The Pile)

Max Activating Token Index: 387

Text #11

Max Range: 0.5881. Min Range: -0.5881

Max Act: 0.3872. Min Act: 0.0000

Data Index: 380827 (The Pile)

Max Activating Token Index: 112

Text #12

Max Range: 0.5881. Min Range: -0.5881

Max Act: 0.3998. Min Act: 0.0000

Data Index: 1456955 (The Pile)

Max Activating Token Index: 642

Text #13

Max Range: 0.5881. Min Range: -0.5881

Max Act: 0.3865. Min Act: -0.0000

Data Index: 433402 (The Pile)

Max Activating Token Index: 290

Text #14

Max Range: 0.5881. Min Range: -0.5881

Max Act: 0.4131. Min Act: -0.0000

Data Index: 1065412 (The Pile)

Max Activating Token Index: 317

Text #15

Max Range: 0.5881. Min Range: -0.5881

Max Act: 0.3941. Min Act: -0.0000

Data Index: 846000 (The Pile)

Max Activating Token Index: 964

Text #16

Max Range: 0.5881. Min Range: -0.5881

Max Act: 0.4020. Min Act: -0.0000

Data Index: 1779316 (The Pile)

Max Activating Token Index: 1000

Text #17

Max Range: 0.5881. Min Range: -0.5881

Max Act: 0.3818. Min Act: -0.0000

Data Index: 157056 (The Pile)

Max Activating Token Index: 581

Text #18

Max Range: 0.5881. Min Range: -0.5881

Max Act: 0.3820. Min Act: -0.0000

Data Index: 820977 (The Pile)

Max Activating Token Index: 345

Text #19

Max Range: 0.5881. Min Range: -0.5881

Max Act: 0.4259. Min Act: -0.0000

Data Index: 1057242 (The Pile)

Max Activating Token Index: 836