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

Dataset: The Pile

Neuron 2515 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: 1.0441. Min Range: -1.0441

Max Act: 1.0046. Min Act: -0.0000

Data Index: 161136 (The Pile)

Max Activating Token Index: 483

Text #1

Max Range: 1.0441. Min Range: -1.0441

Max Act: 1.0108. Min Act: -0.0000

Data Index: 1728387 (The Pile)

Max Activating Token Index: 952

Text #2

Max Range: 1.0441. Min Range: -1.0441

Max Act: 0.9431. Min Act: -0.0000

Data Index: 1017088 (The Pile)

Max Activating Token Index: 83

Text #3

Max Range: 1.0441. Min Range: -1.0441

Max Act: 0.9632. Min Act: -0.0000

Data Index: 82576 (The Pile)

Max Activating Token Index: 852

Text #4

Max Range: 1.0441. Min Range: -1.0441

Max Act: 1.0441. Min Act: -0.0000

Data Index: 1224906 (The Pile)

Max Activating Token Index: 622

Text #5

Max Range: 1.0441. Min Range: -1.0441

Max Act: 0.9474. Min Act: -0.0000

Data Index: 1942386 (The Pile)

Max Activating Token Index: 915

Text #6

Max Range: 1.0441. Min Range: -1.0441

Max Act: 0.8244. Min Act: -0.0000

Data Index: 1658991 (The Pile)

Max Activating Token Index: 918

Text #7

Max Range: 1.0441. Min Range: -1.0441

Max Act: 0.9267. Min Act: -0.0000

Data Index: 569878 (The Pile)

Max Activating Token Index: 78

Text #8

Max Range: 1.0441. Min Range: -1.0441

Max Act: 0.9064. Min Act: -0.0000

Data Index: 128710 (The Pile)

Max Activating Token Index: 79

Text #9

Max Range: 1.0441. Min Range: -1.0441

Max Act: 0.9377. Min Act: -0.0000

Data Index: 197753 (The Pile)

Max Activating Token Index: 156

Text #10

Max Range: 1.0441. Min Range: -1.0441

Max Act: 0.8989. Min Act: -0.0000

Data Index: 373226 (The Pile)

Max Activating Token Index: 362

Text #11

Max Range: 1.0441. Min Range: -1.0441

Max Act: 0.8998. Min Act: -0.0000

Data Index: 821084 (The Pile)

Max Activating Token Index: 402

Text #12

Max Range: 1.0441. Min Range: -1.0441

Max Act: 0.8370. Min Act: -0.0000

Data Index: 1549160 (The Pile)

Max Activating Token Index: 474

Text #13

Max Range: 1.0441. Min Range: -1.0441

Max Act: 0.8759. Min Act: -0.0000

Data Index: 1539710 (The Pile)

Max Activating Token Index: 257

Text #14

Max Range: 1.0441. Min Range: -1.0441

Max Act: 0.8891. Min Act: -0.0000

Data Index: 1051646 (The Pile)

Max Activating Token Index: 521

Text #15

Max Range: 1.0441. Min Range: -1.0441

Max Act: 0.8348. Min Act: -0.0000

Data Index: 1400735 (The Pile)

Max Activating Token Index: 317

Text #16

Max Range: 1.0441. Min Range: -1.0441

Max Act: 0.8799. Min Act: -0.0000

Data Index: 834568 (The Pile)

Max Activating Token Index: 306

Text #17

Max Range: 1.0441. Min Range: -1.0441

Max Act: 0.8927. Min Act: -0.0000

Data Index: 348794 (The Pile)

Max Activating Token Index: 883

Text #18

Max Range: 1.0441. Min Range: -1.0441

Max Act: 0.7496. Min Act: -0.0000

Data Index: 1181191 (The Pile)

Max Activating Token Index: 715

Text #19

Max Range: 1.0441. Min Range: -1.0441

Max Act: 0.9203. Min Act: -0.0000

Data Index: 726165 (The Pile)

Max Activating Token Index: 777