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

Dataset: The Pile

Neuron 4059 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3884. Min Range: -1.3884

Max Act: 1.3884. Min Act: -0.0000

Data Index: 1283064 (The Pile)

Max Activating Token Index: 38

Text #1

Max Range: 1.3884. Min Range: -1.3884

Max Act: 1.3369. Min Act: -0.0000

Data Index: 1355690 (The Pile)

Max Activating Token Index: 349

Text #2

Max Range: 1.3884. Min Range: -1.3884

Max Act: 1.2410. Min Act: -0.0000

Data Index: 1108840 (The Pile)

Max Activating Token Index: 293

Text #3

Max Range: 1.3884. Min Range: -1.3884

Max Act: 1.2672. Min Act: -0.0000

Data Index: 1351831 (The Pile)

Max Activating Token Index: 842

Text #4

Max Range: 1.3884. Min Range: -1.3884

Max Act: 1.1929. Min Act: -0.0000

Data Index: 186222 (The Pile)

Max Activating Token Index: 101

Text #5

Max Range: 1.3884. Min Range: -1.3884

Max Act: 1.1865. Min Act: -0.0000

Data Index: 1315978 (The Pile)

Max Activating Token Index: 191

Text #6

Max Range: 1.3884. Min Range: -1.3884

Max Act: 1.2565. Min Act: -0.0000

Data Index: 229552 (The Pile)

Max Activating Token Index: 225

Text #7

Max Range: 1.3884. Min Range: -1.3884

Max Act: 1.1737. Min Act: -0.0000

Data Index: 1054171 (The Pile)

Max Activating Token Index: 260

Text #8

Max Range: 1.3884. Min Range: -1.3884

Max Act: 1.2059. Min Act: -0.0000

Data Index: 1957227 (The Pile)

Max Activating Token Index: 1008

Text #9

Max Range: 1.3884. Min Range: -1.3884

Max Act: 1.0923. Min Act: -0.0000

Data Index: 317611 (The Pile)

Max Activating Token Index: 499

Text #10

Max Range: 1.3884. Min Range: -1.3884

Max Act: 1.2190. Min Act: -0.0000

Data Index: 546795 (The Pile)

Max Activating Token Index: 214

Text #11

Max Range: 1.3884. Min Range: -1.3884

Max Act: 1.1409. Min Act: -0.0000

Data Index: 1885163 (The Pile)

Max Activating Token Index: 717

Text #12

Max Range: 1.3884. Min Range: -1.3884

Max Act: 1.1103. Min Act: -0.0000

Data Index: 919029 (The Pile)

Max Activating Token Index: 156

Text #13

Max Range: 1.3884. Min Range: -1.3884

Max Act: 1.1584. Min Act: -0.0000

Data Index: 1224964 (The Pile)

Max Activating Token Index: 979

Text #14

Max Range: 1.3884. Min Range: -1.3884

Max Act: 1.0892. Min Act: -0.0000

Data Index: 918435 (The Pile)

Max Activating Token Index: 522

Text #15

Max Range: 1.3884. Min Range: -1.3884

Max Act: 1.0520. Min Act: -0.0000

Data Index: 1813672 (The Pile)

Max Activating Token Index: 329

Text #16

Max Range: 1.3884. Min Range: -1.3884

Max Act: 1.1424. Min Act: -0.0000

Data Index: 1778789 (The Pile)

Max Activating Token Index: 116

Text #17

Max Range: 1.3884. Min Range: -1.3884

Max Act: 1.0571. Min Act: -0.0000

Data Index: 1052997 (The Pile)

Max Activating Token Index: 140

Text #18

Max Range: 1.3884. Min Range: -1.3884

Max Act: 1.0060. Min Act: -0.0000

Data Index: 460977 (The Pile)

Max Activating Token Index: 3

Text #19

Max Range: 1.3884. Min Range: -1.3884

Max Act: 1.0707. Min Act: -0.0000

Data Index: 457686 (The Pile)

Max Activating Token Index: 420