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

Dataset: The Pile

Neuron 938 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3754. Min Range: -0.3754

Max Act: 0.3754. Min Act: -0.0000

Data Index: 950055 (The Pile)

Max Activating Token Index: 326

Text #1

Max Range: 0.3754. Min Range: -0.3754

Max Act: 0.2905. Min Act: -0.0001

Data Index: 1968500 (The Pile)

Max Activating Token Index: 568

Text #2

Max Range: 0.3754. Min Range: -0.3754

Max Act: 0.2988. Min Act: -0.0001

Data Index: 26210 (The Pile)

Max Activating Token Index: 226

Text #3

Max Range: 0.3754. Min Range: -0.3754

Max Act: 0.2817. Min Act: -0.0000

Data Index: 1668154 (The Pile)

Max Activating Token Index: 982

Text #4

Max Range: 0.3754. Min Range: -0.3754

Max Act: 0.2740. Min Act: -0.0000

Data Index: 185486 (The Pile)

Max Activating Token Index: 665

Text #5

Max Range: 0.3754. Min Range: -0.3754

Max Act: 0.2534. Min Act: -0.0000

Data Index: 1218466 (The Pile)

Max Activating Token Index: 778

Text #6

Max Range: 0.3754. Min Range: -0.3754

Max Act: 0.2683. Min Act: -0.0000

Data Index: 288454 (The Pile)

Max Activating Token Index: 384

Text #7

Max Range: 0.3754. Min Range: -0.3754

Max Act: 0.2448. Min Act: -0.0000

Data Index: 908617 (The Pile)

Max Activating Token Index: 938

Text #8

Max Range: 0.3754. Min Range: -0.3754

Max Act: 0.2342. Min Act: -0.0001

Data Index: 517973 (The Pile)

Max Activating Token Index: 882

Text #9

Max Range: 0.3754. Min Range: -0.3754

Max Act: 0.2288. Min Act: -0.0000

Data Index: 1657542 (The Pile)

Max Activating Token Index: 908

Text #10

Max Range: 0.3754. Min Range: -0.3754

Max Act: 0.2251. Min Act: -0.0001

Data Index: 1278940 (The Pile)

Max Activating Token Index: 410

Text #11

Max Range: 0.3754. Min Range: -0.3754

Max Act: 0.2150. Min Act: -0.0001

Data Index: 1551703 (The Pile)

Max Activating Token Index: 822

Text #12

Max Range: 0.3754. Min Range: -0.3754

Max Act: 0.2290. Min Act: -0.0000

Data Index: 562046 (The Pile)

Max Activating Token Index: 654

Text #13

Max Range: 0.3754. Min Range: -0.3754

Max Act: 0.2035. Min Act: -0.0000

Data Index: 811869 (The Pile)

Max Activating Token Index: 947

Text #14

Max Range: 0.3754. Min Range: -0.3754

Max Act: 0.2115. Min Act: -0.0001

Data Index: 1208777 (The Pile)

Max Activating Token Index: 975

Text #15

Max Range: 0.3754. Min Range: -0.3754

Max Act: 0.2136. Min Act: -0.0000

Data Index: 1511654 (The Pile)

Max Activating Token Index: 575

Text #16

Max Range: 0.3754. Min Range: -0.3754

Max Act: 0.2084. Min Act: -0.0000

Data Index: 36193 (The Pile)

Max Activating Token Index: 333

Text #17

Max Range: 0.3754. Min Range: -0.3754

Max Act: 0.2064. Min Act: -0.0001

Data Index: 859668 (The Pile)

Max Activating Token Index: 1001

Text #18

Max Range: 0.3754. Min Range: -0.3754

Max Act: 0.2017. Min Act: -0.0001

Data Index: 550820 (The Pile)

Max Activating Token Index: 263

Text #19

Max Range: 0.3754. Min Range: -0.3754

Max Act: 0.2067. Min Act: -0.0000

Data Index: 717640 (The Pile)

Max Activating Token Index: 827