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

Dataset: The Pile

Neuron 1958 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: 1.0869. Min Range: -1.0869

Max Act: 1.0869. Min Act: -0.0000

Data Index: 100214 (The Pile)

Max Activating Token Index: 475

Text #1

Max Range: 1.0869. Min Range: -1.0869

Max Act: 0.9398. Min Act: -0.0000

Data Index: 1411659 (The Pile)

Max Activating Token Index: 366

Text #2

Max Range: 1.0869. Min Range: -1.0869

Max Act: 0.9919. Min Act: -0.0000

Data Index: 962807 (The Pile)

Max Activating Token Index: 455

Text #3

Max Range: 1.0869. Min Range: -1.0869

Max Act: 0.9146. Min Act: -0.0000

Data Index: 987050 (The Pile)

Max Activating Token Index: 105

Text #4

Max Range: 1.0869. Min Range: -1.0869

Max Act: 0.9044. Min Act: -0.0000

Data Index: 157776 (The Pile)

Max Activating Token Index: 100

Text #5

Max Range: 1.0869. Min Range: -1.0869

Max Act: 0.9228. Min Act: -0.0000

Data Index: 400838 (The Pile)

Max Activating Token Index: 273

Text #6

Max Range: 1.0869. Min Range: -1.0869

Max Act: 0.9357. Min Act: -0.0000

Data Index: 993155 (The Pile)

Max Activating Token Index: 914

Text #7

Max Range: 1.0869. Min Range: -1.0869

Max Act: 0.9840. Min Act: -0.0000

Data Index: 600600 (The Pile)

Max Activating Token Index: 553

Text #8

Max Range: 1.0869. Min Range: -1.0869

Max Act: 0.8957. Min Act: -0.0000

Data Index: 1727877 (The Pile)

Max Activating Token Index: 335

Text #9

Max Range: 1.0869. Min Range: -1.0869

Max Act: 0.8951. Min Act: -0.0000

Data Index: 620046 (The Pile)

Max Activating Token Index: 126

Text #10

Max Range: 1.0869. Min Range: -1.0869

Max Act: 0.8437. Min Act: -0.0000

Data Index: 800927 (The Pile)

Max Activating Token Index: 242

Text #11

Max Range: 1.0869. Min Range: -1.0869

Max Act: 0.8343. Min Act: -0.0000

Data Index: 50135 (The Pile)

Max Activating Token Index: 223

Text #12

Max Range: 1.0869. Min Range: -1.0869

Max Act: 0.8533. Min Act: -0.0000

Data Index: 1202303 (The Pile)

Max Activating Token Index: 484

Text #13

Max Range: 1.0869. Min Range: -1.0869

Max Act: 0.8404. Min Act: -0.0000

Data Index: 958456 (The Pile)

Max Activating Token Index: 65

Text #14

Max Range: 1.0869. Min Range: -1.0869

Max Act: 0.7516. Min Act: -0.0000

Data Index: 330293 (The Pile)

Max Activating Token Index: 839

Text #15

Max Range: 1.0869. Min Range: -1.0869

Max Act: 0.7983. Min Act: -0.0000

Data Index: 756272 (The Pile)

Max Activating Token Index: 224

Text #16

Max Range: 1.0869. Min Range: -1.0869

Max Act: 0.7968. Min Act: -0.0000

Data Index: 503782 (The Pile)

Max Activating Token Index: 876

Text #17

Max Range: 1.0869. Min Range: -1.0869

Max Act: 0.8162. Min Act: -0.0000

Data Index: 1712646 (The Pile)

Max Activating Token Index: 889

Text #18

Max Range: 1.0869. Min Range: -1.0869

Max Act: 0.7991. Min Act: -0.0000

Data Index: 409428 (The Pile)

Max Activating Token Index: 455

Text #19

Max Range: 1.0869. Min Range: -1.0869

Max Act: 0.7449. Min Act: -0.0000

Data Index: 585984 (The Pile)

Max Activating Token Index: 705