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

Dataset: The Pile

Neuron 4820 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5514. Min Range: -0.5514

Max Act: 0.5514. Min Act: -0.0001

Data Index: 512750 (The Pile)

Max Activating Token Index: 656

Text #1

Max Range: 0.5514. Min Range: -0.5514

Max Act: 0.5147. Min Act: -0.0000

Data Index: 143393 (The Pile)

Max Activating Token Index: 866

Text #2

Max Range: 0.5514. Min Range: -0.5514

Max Act: 0.5405. Min Act: -0.0001

Data Index: 1013724 (The Pile)

Max Activating Token Index: 340

Text #3

Max Range: 0.5514. Min Range: -0.5514

Max Act: 0.5276. Min Act: -0.0000

Data Index: 1872713 (The Pile)

Max Activating Token Index: 760

Text #4

Max Range: 0.5514. Min Range: -0.5514

Max Act: 0.5131. Min Act: -0.0000

Data Index: 996898 (The Pile)

Max Activating Token Index: 207

Text #5

Max Range: 0.5514. Min Range: -0.5514

Max Act: 0.5269. Min Act: -0.0000

Data Index: 1844324 (The Pile)

Max Activating Token Index: 779

Text #6

Max Range: 0.5514. Min Range: -0.5514

Max Act: 0.5506. Min Act: -0.0000

Data Index: 1175868 (The Pile)

Max Activating Token Index: 994

Text #7

Max Range: 0.5514. Min Range: -0.5514

Max Act: 0.4730. Min Act: -0.0001

Data Index: 1716132 (The Pile)

Max Activating Token Index: 621

Text #8

Max Range: 0.5514. Min Range: -0.5514

Max Act: 0.4952. Min Act: -0.0001

Data Index: 1988254 (The Pile)

Max Activating Token Index: 91

Text #9

Max Range: 0.5514. Min Range: -0.5514

Max Act: 0.4966. Min Act: -0.0001

Data Index: 1587904 (The Pile)

Max Activating Token Index: 726

Text #10

Max Range: 0.5514. Min Range: -0.5514

Max Act: 0.5198. Min Act: -0.0000

Data Index: 931382 (The Pile)

Max Activating Token Index: 352

Text #11

Max Range: 0.5514. Min Range: -0.5514

Max Act: 0.5049. Min Act: -0.0000

Data Index: 488745 (The Pile)

Max Activating Token Index: 482

Text #12

Max Range: 0.5514. Min Range: -0.5514

Max Act: 0.5204. Min Act: -0.0000

Data Index: 620095 (The Pile)

Max Activating Token Index: 116

Text #13

Max Range: 0.5514. Min Range: -0.5514

Max Act: 0.4917. Min Act: -0.0000

Data Index: 1119233 (The Pile)

Max Activating Token Index: 601

Text #14

Max Range: 0.5514. Min Range: -0.5514

Max Act: 0.5008. Min Act: -0.0000

Data Index: 450090 (The Pile)

Max Activating Token Index: 86

Text #15

Max Range: 0.5514. Min Range: -0.5514

Max Act: 0.4810. Min Act: -0.0000

Data Index: 1906018 (The Pile)

Max Activating Token Index: 892

Text #16

Max Range: 0.5514. Min Range: -0.5514

Max Act: 0.5202. Min Act: -0.0000

Data Index: 350885 (The Pile)

Max Activating Token Index: 296

Text #17

Max Range: 0.5514. Min Range: -0.5514

Max Act: 0.4909. Min Act: -0.0000

Data Index: 1700533 (The Pile)

Max Activating Token Index: 94

Text #18

Max Range: 0.5514. Min Range: -0.5514

Max Act: 0.5046. Min Act: -0.0001

Data Index: 1356707 (The Pile)

Max Activating Token Index: 398

Text #19

Max Range: 0.5514. Min Range: -0.5514

Max Act: 0.5056. Min Act: -0.0000

Data Index: 42111 (The Pile)

Max Activating Token Index: 339