Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 31 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')

Text #0

Max Range: 0.3544. Min Range: -0.3544

Max Act: 0.3544. Min Act: -0.0000

Data Index: 1187970 (The Pile)

Max Activating Token Index: 836

Text #1

Max Range: 0.3544. Min Range: -0.3544

Max Act: 0.3504. Min Act: -0.0000

Data Index: 17114 (The Pile)

Max Activating Token Index: 31

Text #2

Max Range: 0.3544. Min Range: -0.3544

Max Act: 0.3181. Min Act: -0.0000

Data Index: 866700 (The Pile)

Max Activating Token Index: 117

Text #3

Max Range: 0.3544. Min Range: -0.3544

Max Act: 0.3190. Min Act: -0.0000

Data Index: 483261 (The Pile)

Max Activating Token Index: 888

Text #4

Max Range: 0.3544. Min Range: -0.3544

Max Act: 0.3118. Min Act: -0.0000

Data Index: 1442758 (The Pile)

Max Activating Token Index: 1019

Text #5

Max Range: 0.3544. Min Range: -0.3544

Max Act: 0.2987. Min Act: -0.0000

Data Index: 1094571 (The Pile)

Max Activating Token Index: 404

Text #6

Max Range: 0.3544. Min Range: -0.3544

Max Act: 0.3077. Min Act: -0.0000

Data Index: 1380183 (The Pile)

Max Activating Token Index: 308

Text #7

Max Range: 0.3544. Min Range: -0.3544

Max Act: 0.3007. Min Act: -0.0000

Data Index: 1824332 (The Pile)

Max Activating Token Index: 61

Text #8

Max Range: 0.3544. Min Range: -0.3544

Max Act: 0.2958. Min Act: -0.0000

Data Index: 1000714 (The Pile)

Max Activating Token Index: 547

Text #9

Max Range: 0.3544. Min Range: -0.3544

Max Act: 0.2931. Min Act: -0.0000

Data Index: 1132433 (The Pile)

Max Activating Token Index: 620

Text #10

Max Range: 0.3544. Min Range: -0.3544

Max Act: 0.2919. Min Act: -0.0000

Data Index: 184697 (The Pile)

Max Activating Token Index: 602

Text #11

Max Range: 0.3544. Min Range: -0.3544

Max Act: 0.2817. Min Act: -0.0000

Data Index: 1234180 (The Pile)

Max Activating Token Index: 1000

Text #12

Max Range: 0.3544. Min Range: -0.3544

Max Act: 0.2973. Min Act: -0.0000

Data Index: 47292 (The Pile)

Max Activating Token Index: 208

Text #13

Max Range: 0.3544. Min Range: -0.3544

Max Act: 0.2866. Min Act: -0.0000

Data Index: 1114249 (The Pile)

Max Activating Token Index: 381

Text #14

Max Range: 0.3544. Min Range: -0.3544

Max Act: 0.2875. Min Act: -0.0000

Data Index: 837687 (The Pile)

Max Activating Token Index: 796

Text #15

Max Range: 0.3544. Min Range: -0.3544

Max Act: 0.2850. Min Act: -0.0000

Data Index: 1151901 (The Pile)

Max Activating Token Index: 973

Text #16

Max Range: 0.3544. Min Range: -0.3544

Max Act: 0.2848. Min Act: -0.0000

Data Index: 1202244 (The Pile)

Max Activating Token Index: 295

Text #17

Max Range: 0.3544. Min Range: -0.3544

Max Act: 0.2924. Min Act: -0.0001

Data Index: 564484 (The Pile)

Max Activating Token Index: 140

Text #18

Max Range: 0.3544. Min Range: -0.3544

Max Act: 0.2828. Min Act: -0.0000

Data Index: 1835694 (The Pile)

Max Activating Token Index: 625

Text #19

Max Range: 0.3544. Min Range: -0.3544

Max Act: 0.2732. Min Act: -0.0000

Data Index: 297656 (The Pile)

Max Activating Token Index: 777