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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 4970 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0664. Min Act: -0.0002

Data Index: 184294 (C4 (Web Text))

Max Activating Token Index: 139

Text #1

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0554. Min Act: -0.0002

Data Index: 494303 (C4 (Web Text))

Max Activating Token Index: 991

Text #2

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0572. Min Act: -0.0002

Data Index: 1182817 (C4 (Web Text))

Max Activating Token Index: 883

Text #3

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0538. Min Act: -0.0002

Data Index: 1018791 (C4 (Web Text))

Max Activating Token Index: 137

Text #4

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0521. Min Act: -0.0002

Data Index: 142 (C4 (Web Text))

Max Activating Token Index: 852

Text #5

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0498. Min Act: -0.0002

Data Index: 117046 (C4 (Web Text))

Max Activating Token Index: 850

Text #6

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0493. Min Act: -0.0002

Data Index: 506394 (C4 (Web Text))

Max Activating Token Index: 171

Text #7

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0478. Min Act: -0.0002

Data Index: 977063 (C4 (Web Text))

Max Activating Token Index: 239

Text #8

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0477. Min Act: -0.0002

Data Index: 160360 (C4 (Web Text))

Max Activating Token Index: 886

Text #9

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0463. Min Act: -0.0002

Data Index: 575022 (C4 (Web Text))

Max Activating Token Index: 155

Text #10

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0457. Min Act: -0.0002

Data Index: 96257 (C4 (Web Text))

Max Activating Token Index: 285

Text #11

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0470. Min Act: -0.0002

Data Index: 1288934 (C4 (Web Text))

Max Activating Token Index: 348

Text #12

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0473. Min Act: -0.0002

Data Index: 721434 (C4 (Web Text))

Max Activating Token Index: 170

Text #13

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0445. Min Act: -0.0002

Data Index: 1334104 (C4 (Web Text))

Max Activating Token Index: 349

Text #14

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0468. Min Act: -0.0002

Data Index: 26196 (C4 (Web Text))

Max Activating Token Index: 833

Text #15

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0474. Min Act: -0.0002

Data Index: 910336 (C4 (Web Text))

Max Activating Token Index: 896

Text #16

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0419. Min Act: -0.0002

Data Index: 62784 (C4 (Web Text))

Max Activating Token Index: 310

Text #17

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0465. Min Act: -0.0002

Data Index: 656385 (C4 (Web Text))

Max Activating Token Index: 851

Text #18

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0448. Min Act: -0.0002

Data Index: 1296058 (C4 (Web Text))

Max Activating Token Index: 640

Text #19

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0464. Min Act: -0.0002

Data Index: 724464 (C4 (Web Text))

Max Activating Token Index: 329