Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 395 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.6981. Min Range: -0.6981

Max Act: 0.6765. Min Act: -0.0000

Data Index: 1875843 (The Pile)

Max Activating Token Index: 915

Text #1

Max Range: 0.6981. Min Range: -0.6981

Max Act: 0.6229. Min Act: -0.0000

Data Index: 656338 (The Pile)

Max Activating Token Index: 885

Text #2

Max Range: 0.6981. Min Range: -0.6981

Max Act: 0.6981. Min Act: -0.0000

Data Index: 996521 (The Pile)

Max Activating Token Index: 568

Text #3

Max Range: 0.6981. Min Range: -0.6981

Max Act: 0.6963. Min Act: -0.0000

Data Index: 1022382 (The Pile)

Max Activating Token Index: 358

Text #4

Max Range: 0.6981. Min Range: -0.6981

Max Act: 0.6086. Min Act: -0.0000

Data Index: 488240 (The Pile)

Max Activating Token Index: 832

Text #5

Max Range: 0.6981. Min Range: -0.6981

Max Act: 0.6929. Min Act: -0.0000

Data Index: 1538679 (The Pile)

Max Activating Token Index: 481

Text #6

Max Range: 0.6981. Min Range: -0.6981

Max Act: 0.6343. Min Act: -0.0000

Data Index: 1545572 (The Pile)

Max Activating Token Index: 898

Text #7

Max Range: 0.6981. Min Range: -0.6981

Max Act: 0.5810. Min Act: -0.0000

Data Index: 1067953 (The Pile)

Max Activating Token Index: 425

Text #8

Max Range: 0.6981. Min Range: -0.6981

Max Act: 0.6026. Min Act: -0.0000

Data Index: 336337 (The Pile)

Max Activating Token Index: 326

Text #9

Max Range: 0.6981. Min Range: -0.6981

Max Act: 0.6353. Min Act: -0.0000

Data Index: 865942 (The Pile)

Max Activating Token Index: 752

Text #10

Max Range: 0.6981. Min Range: -0.6981

Max Act: 0.6102. Min Act: -0.0000

Data Index: 901284 (The Pile)

Max Activating Token Index: 739

Text #11

Max Range: 0.6981. Min Range: -0.6981

Max Act: 0.6682. Min Act: -0.0000

Data Index: 904872 (The Pile)

Max Activating Token Index: 681

Text #12

Max Range: 0.6981. Min Range: -0.6981

Max Act: 0.6090. Min Act: -0.0000

Data Index: 181465 (The Pile)

Max Activating Token Index: 937

Text #13

Max Range: 0.6981. Min Range: -0.6981

Max Act: 0.6097. Min Act: -0.0000

Data Index: 1017890 (The Pile)

Max Activating Token Index: 290

Text #14

Max Range: 0.6981. Min Range: -0.6981

Max Act: 0.6052. Min Act: -0.0000

Data Index: 217434 (The Pile)

Max Activating Token Index: 379

Text #15

Max Range: 0.6981. Min Range: -0.6981

Max Act: 0.6034. Min Act: -0.0000

Data Index: 1957637 (The Pile)

Max Activating Token Index: 458

Text #16

Max Range: 0.6981. Min Range: -0.6981

Max Act: 0.6447. Min Act: -0.0000

Data Index: 1528733 (The Pile)

Max Activating Token Index: 857

Text #17

Max Range: 0.6981. Min Range: -0.6981

Max Act: 0.6459. Min Act: -0.0000

Data Index: 1558428 (The Pile)

Max Activating Token Index: 899

Text #18

Max Range: 0.6981. Min Range: -0.6981

Max Act: 0.6227. Min Act: -0.0000

Data Index: 499045 (The Pile)

Max Activating Token Index: 646

Text #19

Max Range: 0.6981. Min Range: -0.6981

Max Act: 0.6520. Min Act: -0.0000

Data Index: 1188015 (The Pile)

Max Activating Token Index: 485