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

Dataset: The Pile

Neuron 4402 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0924. Min Range: -1.0924

Max Act: 1.0924. Min Act: -0.0000

Data Index: 1055636 (The Pile)

Max Activating Token Index: 130

Text #1

Max Range: 1.0924. Min Range: -1.0924

Max Act: 0.9610. Min Act: -0.0000

Data Index: 742621 (The Pile)

Max Activating Token Index: 444

Text #2

Max Range: 1.0924. Min Range: -1.0924

Max Act: 0.9696. Min Act: -0.0000

Data Index: 1077100 (The Pile)

Max Activating Token Index: 313

Text #3

Max Range: 1.0924. Min Range: -1.0924

Max Act: 0.9252. Min Act: -0.0000

Data Index: 772753 (The Pile)

Max Activating Token Index: 944

Text #4

Max Range: 1.0924. Min Range: -1.0924

Max Act: 0.8557. Min Act: -0.0000

Data Index: 1589540 (The Pile)

Max Activating Token Index: 268

Text #5

Max Range: 1.0924. Min Range: -1.0924

Max Act: 0.8476. Min Act: -0.0000

Data Index: 1664693 (The Pile)

Max Activating Token Index: 506

Text #6

Max Range: 1.0924. Min Range: -1.0924

Max Act: 0.8420. Min Act: 0.0000

Data Index: 1893977 (The Pile)

Max Activating Token Index: 472

Text #7

Max Range: 1.0924. Min Range: -1.0924

Max Act: 0.8465. Min Act: -0.0000

Data Index: 1160982 (The Pile)

Max Activating Token Index: 234

Text #8

Max Range: 1.0924. Min Range: -1.0924

Max Act: 0.8405. Min Act: -0.0000

Data Index: 163449 (The Pile)

Max Activating Token Index: 113

Text #9

Max Range: 1.0924. Min Range: -1.0924

Max Act: 0.8929. Min Act: -0.0000

Data Index: 552046 (The Pile)

Max Activating Token Index: 636

Text #10

Max Range: 1.0924. Min Range: -1.0924

Max Act: 0.8621. Min Act: -0.0000

Data Index: 342785 (The Pile)

Max Activating Token Index: 34

Text #11

Max Range: 1.0924. Min Range: -1.0924

Max Act: 0.8370. Min Act: -0.0000

Data Index: 1152862 (The Pile)

Max Activating Token Index: 999

Text #12

Max Range: 1.0924. Min Range: -1.0924

Max Act: 0.8589. Min Act: -0.0000

Data Index: 750082 (The Pile)

Max Activating Token Index: 533

Text #13

Max Range: 1.0924. Min Range: -1.0924

Max Act: 0.7927. Min Act: -0.0000

Data Index: 395381 (The Pile)

Max Activating Token Index: 84

Text #14

Max Range: 1.0924. Min Range: -1.0924

Max Act: 0.8169. Min Act: -0.0000

Data Index: 1533644 (The Pile)

Max Activating Token Index: 20

Text #15

Max Range: 1.0924. Min Range: -1.0924

Max Act: 0.8097. Min Act: -0.0000

Data Index: 443058 (The Pile)

Max Activating Token Index: 92

Text #16

Max Range: 1.0924. Min Range: -1.0924

Max Act: 0.7785. Min Act: -0.0000

Data Index: 1474648 (The Pile)

Max Activating Token Index: 672

Text #17

Max Range: 1.0924. Min Range: -1.0924

Max Act: 0.7979. Min Act: -0.0000

Data Index: 1822223 (The Pile)

Max Activating Token Index: 1009

Text #18

Max Range: 1.0924. Min Range: -1.0924

Max Act: 0.8154. Min Act: -0.0000

Data Index: 1732319 (The Pile)

Max Activating Token Index: 178

Text #19

Max Range: 1.0924. Min Range: -1.0924

Max Act: 0.7373. Min Act: -0.0000

Data Index: 1320646 (The Pile)

Max Activating Token Index: 624