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

Dataset: The Pile

Neuron 3916 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: 3.9185. Min Range: -3.9185

Max Act: 3.6081. Min Act: -0.0000

Data Index: 1669463 (The Pile)

Max Activating Token Index: 195

Text #1

Max Range: 3.9185. Min Range: -3.9185

Max Act: 3.9185. Min Act: -0.0000

Data Index: 1500337 (The Pile)

Max Activating Token Index: 661

Text #2

Max Range: 3.9185. Min Range: -3.9185

Max Act: 3.6213. Min Act: -0.0000

Data Index: 613562 (The Pile)

Max Activating Token Index: 386

Text #3

Max Range: 3.9185. Min Range: -3.9185

Max Act: 3.9088. Min Act: -0.0000

Data Index: 886084 (The Pile)

Max Activating Token Index: 476

Text #4

Max Range: 3.9185. Min Range: -3.9185

Max Act: 3.5298. Min Act: -0.0000

Data Index: 1224125 (The Pile)

Max Activating Token Index: 758

Text #5

Max Range: 3.9185. Min Range: -3.9185

Max Act: 3.2718. Min Act: -0.0000

Data Index: 50107 (The Pile)

Max Activating Token Index: 660

Text #6

Max Range: 3.9185. Min Range: -3.9185

Max Act: 3.5254. Min Act: -0.0000

Data Index: 1221847 (The Pile)

Max Activating Token Index: 71

Text #7

Max Range: 3.9185. Min Range: -3.9185

Max Act: 3.0502. Min Act: -0.0000

Data Index: 630703 (The Pile)

Max Activating Token Index: 93

Text #8

Max Range: 3.9185. Min Range: -3.9185

Max Act: 3.4536. Min Act: -0.0000

Data Index: 346984 (The Pile)

Max Activating Token Index: 578

Text #9

Max Range: 3.9185. Min Range: -3.9185

Max Act: 3.4550. Min Act: -0.0000

Data Index: 386705 (The Pile)

Max Activating Token Index: 578

Text #10

Max Range: 3.9185. Min Range: -3.9185

Max Act: 3.2686. Min Act: -0.0000

Data Index: 995010 (The Pile)

Max Activating Token Index: 74

Text #11

Max Range: 3.9185. Min Range: -3.9185

Max Act: 2.9671. Min Act: -0.0000

Data Index: 1217824 (The Pile)

Max Activating Token Index: 970

Text #12

Max Range: 3.9185. Min Range: -3.9185

Max Act: 2.9729. Min Act: -0.0000

Data Index: 619520 (The Pile)

Max Activating Token Index: 728

Text #13

Max Range: 3.9185. Min Range: -3.9185

Max Act: 3.2325. Min Act: -0.0000

Data Index: 380978 (The Pile)

Max Activating Token Index: 73

Text #14

Max Range: 3.9185. Min Range: -3.9185

Max Act: 3.2513. Min Act: -0.0000

Data Index: 1479482 (The Pile)

Max Activating Token Index: 81

Text #15

Max Range: 3.9185. Min Range: -3.9185

Max Act: 3.0551. Min Act: -0.0000

Data Index: 1048147 (The Pile)

Max Activating Token Index: 369

Text #16

Max Range: 3.9185. Min Range: -3.9185

Max Act: 3.2977. Min Act: -0.0000

Data Index: 329715 (The Pile)

Max Activating Token Index: 357

Text #17

Max Range: 3.9185. Min Range: -3.9185

Max Act: 3.0231. Min Act: -0.0000

Data Index: 1320827 (The Pile)

Max Activating Token Index: 336

Text #18

Max Range: 3.9185. Min Range: -3.9185

Max Act: 2.8554. Min Act: -0.0000

Data Index: 1824883 (The Pile)

Max Activating Token Index: 254

Text #19

Max Range: 3.9185. Min Range: -3.9185

Max Act: 3.0741. Min Act: -0.0000

Data Index: 473092 (The Pile)

Max Activating Token Index: 47