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

Dataset: The Pile

Neuron 2263 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0329. Min Range: -1.0329

Max Act: 1.0329. Min Act: -0.0000

Data Index: 1944188 (The Pile)

Max Activating Token Index: 68

Text #1

Max Range: 1.0329. Min Range: -1.0329

Max Act: 0.9915. Min Act: -0.0000

Data Index: 1321418 (The Pile)

Max Activating Token Index: 149

Text #2

Max Range: 1.0329. Min Range: -1.0329

Max Act: 1.0017. Min Act: -0.0000

Data Index: 1659925 (The Pile)

Max Activating Token Index: 809

Text #3

Max Range: 1.0329. Min Range: -1.0329

Max Act: 0.9533. Min Act: -0.0000

Data Index: 796921 (The Pile)

Max Activating Token Index: 649

Text #4

Max Range: 1.0329. Min Range: -1.0329

Max Act: 0.9490. Min Act: -0.0000

Data Index: 240276 (The Pile)

Max Activating Token Index: 76

Text #5

Max Range: 1.0329. Min Range: -1.0329

Max Act: 0.8964. Min Act: -0.0000

Data Index: 451082 (The Pile)

Max Activating Token Index: 851

Text #6

Max Range: 1.0329. Min Range: -1.0329

Max Act: 0.9210. Min Act: -0.0000

Data Index: 463341 (The Pile)

Max Activating Token Index: 431

Text #7

Max Range: 1.0329. Min Range: -1.0329

Max Act: 0.7872. Min Act: -0.0000

Data Index: 353318 (The Pile)

Max Activating Token Index: 638

Text #8

Max Range: 1.0329. Min Range: -1.0329

Max Act: 0.9102. Min Act: -0.0000

Data Index: 600797 (The Pile)

Max Activating Token Index: 585

Text #9

Max Range: 1.0329. Min Range: -1.0329

Max Act: 0.8787. Min Act: -0.0000

Data Index: 609481 (The Pile)

Max Activating Token Index: 361

Text #10

Max Range: 1.0329. Min Range: -1.0329

Max Act: 0.8450. Min Act: -0.0000

Data Index: 65649 (The Pile)

Max Activating Token Index: 293

Text #11

Max Range: 1.0329. Min Range: -1.0329

Max Act: 0.8315. Min Act: -0.0000

Data Index: 115760 (The Pile)

Max Activating Token Index: 461

Text #12

Max Range: 1.0329. Min Range: -1.0329

Max Act: 0.7778. Min Act: -0.0000

Data Index: 437294 (The Pile)

Max Activating Token Index: 92

Text #13

Max Range: 1.0329. Min Range: -1.0329

Max Act: 0.7764. Min Act: -0.0000

Data Index: 982154 (The Pile)

Max Activating Token Index: 698

Text #14

Max Range: 1.0329. Min Range: -1.0329

Max Act: 0.8762. Min Act: -0.0000

Data Index: 1538858 (The Pile)

Max Activating Token Index: 301

Text #15

Max Range: 1.0329. Min Range: -1.0329

Max Act: 0.7961. Min Act: -0.0000

Data Index: 1703731 (The Pile)

Max Activating Token Index: 485

Text #16

Max Range: 1.0329. Min Range: -1.0329

Max Act: 0.8227. Min Act: -0.0000

Data Index: 538341 (The Pile)

Max Activating Token Index: 423

Text #17

Max Range: 1.0329. Min Range: -1.0329

Max Act: 0.7876. Min Act: -0.0000

Data Index: 1465310 (The Pile)

Max Activating Token Index: 924

Text #18

Max Range: 1.0329. Min Range: -1.0329

Max Act: 0.8118. Min Act: -0.0000

Data Index: 267901 (The Pile)

Max Activating Token Index: 783

Text #19

Max Range: 1.0329. Min Range: -1.0329

Max Act: 0.8134. Min Act: -0.0000

Data Index: 1986925 (The Pile)

Max Activating Token Index: 403