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

Dataset: The Pile

Neuron 2434 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8267. Min Range: -1.8267

Max Act: 1.8267. Min Act: -0.0000

Data Index: 1947029 (The Pile)

Max Activating Token Index: 495

Text #1

Max Range: 1.8267. Min Range: -1.8267

Max Act: 1.5251. Min Act: -0.0000

Data Index: 1137245 (The Pile)

Max Activating Token Index: 904

Text #2

Max Range: 1.8267. Min Range: -1.8267

Max Act: 1.6827. Min Act: -0.0000

Data Index: 742306 (The Pile)

Max Activating Token Index: 56

Text #3

Max Range: 1.8267. Min Range: -1.8267

Max Act: 1.7084. Min Act: -0.0000

Data Index: 1076299 (The Pile)

Max Activating Token Index: 193

Text #4

Max Range: 1.8267. Min Range: -1.8267

Max Act: 1.6577. Min Act: -0.0000

Data Index: 302551 (The Pile)

Max Activating Token Index: 668

Text #5

Max Range: 1.8267. Min Range: -1.8267

Max Act: 1.5764. Min Act: -0.0000

Data Index: 1916071 (The Pile)

Max Activating Token Index: 19

Text #6

Max Range: 1.8267. Min Range: -1.8267

Max Act: 1.4974. Min Act: -0.0000

Data Index: 426346 (The Pile)

Max Activating Token Index: 390

Text #7

Max Range: 1.8267. Min Range: -1.8267

Max Act: 1.5871. Min Act: -0.0000

Data Index: 237185 (The Pile)

Max Activating Token Index: 539

Text #8

Max Range: 1.8267. Min Range: -1.8267

Max Act: 1.3843. Min Act: -0.0000

Data Index: 1137009 (The Pile)

Max Activating Token Index: 958

Text #9

Max Range: 1.8267. Min Range: -1.8267

Max Act: 1.5472. Min Act: -0.0000

Data Index: 1043270 (The Pile)

Max Activating Token Index: 668

Text #10

Max Range: 1.8267. Min Range: -1.8267

Max Act: 1.5582. Min Act: -0.0000

Data Index: 456124 (The Pile)

Max Activating Token Index: 996

Text #11

Max Range: 1.8267. Min Range: -1.8267

Max Act: 1.4411. Min Act: -0.0000

Data Index: 809199 (The Pile)

Max Activating Token Index: 157

Text #12

Max Range: 1.8267. Min Range: -1.8267

Max Act: 1.4531. Min Act: -0.0000

Data Index: 1979898 (The Pile)

Max Activating Token Index: 338

Text #13

Max Range: 1.8267. Min Range: -1.8267

Max Act: 1.5204. Min Act: -0.0000

Data Index: 728596 (The Pile)

Max Activating Token Index: 66

Text #14

Max Range: 1.8267. Min Range: -1.8267

Max Act: 1.4373. Min Act: -0.0000

Data Index: 1009795 (The Pile)

Max Activating Token Index: 779

Text #15

Max Range: 1.8267. Min Range: -1.8267

Max Act: 1.5159. Min Act: -0.0000

Data Index: 61932 (The Pile)

Max Activating Token Index: 942

Text #16

Max Range: 1.8267. Min Range: -1.8267

Max Act: 1.5090. Min Act: -0.0000

Data Index: 1242685 (The Pile)

Max Activating Token Index: 328

Text #17

Max Range: 1.8267. Min Range: -1.8267

Max Act: 1.4131. Min Act: -0.0000

Data Index: 1291826 (The Pile)

Max Activating Token Index: 279

Text #18

Max Range: 1.8267. Min Range: -1.8267

Max Act: 1.3813. Min Act: -0.0000

Data Index: 659029 (The Pile)

Max Activating Token Index: 499

Text #19

Max Range: 1.8267. Min Range: -1.8267

Max Act: 1.5120. Min Act: -0.0000

Data Index: 1058696 (The Pile)

Max Activating Token Index: 614