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

Dataset: The Pile

Neuron 2730 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: 1.0482. Min Range: -1.0482

Max Act: 1.0482. Min Act: -0.0000

Data Index: 405485 (The Pile)

Max Activating Token Index: 110

Text #1

Max Range: 1.0482. Min Range: -1.0482

Max Act: 0.8877. Min Act: -0.0000

Data Index: 1955152 (The Pile)

Max Activating Token Index: 339

Text #2

Max Range: 1.0482. Min Range: -1.0482

Max Act: 0.9753. Min Act: -0.0000

Data Index: 363471 (The Pile)

Max Activating Token Index: 999

Text #3

Max Range: 1.0482. Min Range: -1.0482

Max Act: 0.8899. Min Act: -0.0000

Data Index: 385123 (The Pile)

Max Activating Token Index: 204

Text #4

Max Range: 1.0482. Min Range: -1.0482

Max Act: 0.8565. Min Act: -0.0000

Data Index: 133760 (The Pile)

Max Activating Token Index: 720

Text #5

Max Range: 1.0482. Min Range: -1.0482

Max Act: 0.8435. Min Act: -0.0001

Data Index: 216866 (The Pile)

Max Activating Token Index: 849

Text #6

Max Range: 1.0482. Min Range: -1.0482

Max Act: 0.8556. Min Act: -0.0000

Data Index: 1281796 (The Pile)

Max Activating Token Index: 285

Text #7

Max Range: 1.0482. Min Range: -1.0482

Max Act: 0.7940. Min Act: -0.0000

Data Index: 588389 (The Pile)

Max Activating Token Index: 151

Text #8

Max Range: 1.0482. Min Range: -1.0482

Max Act: 0.7524. Min Act: -0.0000

Data Index: 1633306 (The Pile)

Max Activating Token Index: 646

Text #9

Max Range: 1.0482. Min Range: -1.0482

Max Act: 0.7778. Min Act: -0.0001

Data Index: 1684527 (The Pile)

Max Activating Token Index: 81

Text #10

Max Range: 1.0482. Min Range: -1.0482

Max Act: 0.7578. Min Act: -0.0000

Data Index: 431914 (The Pile)

Max Activating Token Index: 987

Text #11

Max Range: 1.0482. Min Range: -1.0482

Max Act: 0.7131. Min Act: -0.0000

Data Index: 268794 (The Pile)

Max Activating Token Index: 879

Text #12

Max Range: 1.0482. Min Range: -1.0482

Max Act: 0.7767. Min Act: -0.0001

Data Index: 1632327 (The Pile)

Max Activating Token Index: 433

Text #13

Max Range: 1.0482. Min Range: -1.0482

Max Act: 0.7541. Min Act: -0.0000

Data Index: 639542 (The Pile)

Max Activating Token Index: 680

Text #14

Max Range: 1.0482. Min Range: -1.0482

Max Act: 0.6713. Min Act: -0.0000

Data Index: 176817 (The Pile)

Max Activating Token Index: 222

Text #15

Max Range: 1.0482. Min Range: -1.0482

Max Act: 0.7330. Min Act: -0.0000

Data Index: 1549141 (The Pile)

Max Activating Token Index: 566

Text #16

Max Range: 1.0482. Min Range: -1.0482

Max Act: 0.7201. Min Act: -0.0000

Data Index: 825297 (The Pile)

Max Activating Token Index: 682

Text #17

Max Range: 1.0482. Min Range: -1.0482

Max Act: 0.6948. Min Act: -0.0000

Data Index: 295446 (The Pile)

Max Activating Token Index: 91

Text #18

Max Range: 1.0482. Min Range: -1.0482

Max Act: 0.7367. Min Act: -0.0000

Data Index: 1130437 (The Pile)

Max Activating Token Index: 590

Text #19

Max Range: 1.0482. Min Range: -1.0482

Max Act: 0.6791. Min Act: -0.0000

Data Index: 492564 (The Pile)

Max Activating Token Index: 250