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

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

Neuron 426 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1529. Min Range: -2.1529

Max Act: 2.1529. Min Act: -0.0000

Data Index: 1021786 (C4 (Web Text))

Max Activating Token Index: 440

Text #1

Max Range: 2.1529. Min Range: -2.1529

Max Act: 2.1218. Min Act: -0.0000

Data Index: 387848 (C4 (Web Text))

Max Activating Token Index: 796

Text #2

Max Range: 2.1529. Min Range: -2.1529

Max Act: 1.8126. Min Act: -0.0000

Data Index: 249091 (C4 (Web Text))

Max Activating Token Index: 283

Text #3

Max Range: 2.1529. Min Range: -2.1529

Max Act: 1.9824. Min Act: -0.0000

Data Index: 372594 (C4 (Web Text))

Max Activating Token Index: 106

Text #4

Max Range: 2.1529. Min Range: -2.1529

Max Act: 1.6329. Min Act: -0.0000

Data Index: 1197448 (C4 (Web Text))

Max Activating Token Index: 379

Text #5

Max Range: 2.1529. Min Range: -2.1529

Max Act: 1.5569. Min Act: -0.0000

Data Index: 829979 (C4 (Web Text))

Max Activating Token Index: 188

Text #6

Max Range: 2.1529. Min Range: -2.1529

Max Act: 1.6139. Min Act: -0.0000

Data Index: 144893 (C4 (Web Text))

Max Activating Token Index: 399

Text #7

Max Range: 2.1529. Min Range: -2.1529

Max Act: 1.4660. Min Act: -0.0000

Data Index: 767960 (C4 (Web Text))

Max Activating Token Index: 668

Text #8

Max Range: 2.1529. Min Range: -2.1529

Max Act: 1.5994. Min Act: -0.0000

Data Index: 335990 (C4 (Web Text))

Max Activating Token Index: 389

Text #9

Max Range: 2.1529. Min Range: -2.1529

Max Act: 1.5200. Min Act: -0.0000

Data Index: 509642 (C4 (Web Text))

Max Activating Token Index: 575

Text #10

Max Range: 2.1529. Min Range: -2.1529

Max Act: 1.5187. Min Act: -0.0000

Data Index: 1357774 (C4 (Web Text))

Max Activating Token Index: 122

Text #11

Max Range: 2.1529. Min Range: -2.1529

Max Act: 1.5979. Min Act: -0.0000

Data Index: 623610 (C4 (Web Text))

Max Activating Token Index: 864

Text #12

Max Range: 2.1529. Min Range: -2.1529

Max Act: 1.6409. Min Act: -0.0000

Data Index: 108973 (C4 (Web Text))

Max Activating Token Index: 289

Text #13

Max Range: 2.1529. Min Range: -2.1529

Max Act: 1.4950. Min Act: -0.0000

Data Index: 278704 (C4 (Web Text))

Max Activating Token Index: 709

Text #14

Max Range: 2.1529. Min Range: -2.1529

Max Act: 1.4682. Min Act: -0.0000

Data Index: 573394 (C4 (Web Text))

Max Activating Token Index: 804

Text #15

Max Range: 2.1529. Min Range: -2.1529

Max Act: 1.6819. Min Act: -0.0000

Data Index: 69121 (C4 (Web Text))

Max Activating Token Index: 655

Text #16

Max Range: 2.1529. Min Range: -2.1529

Max Act: 1.4701. Min Act: -0.0000

Data Index: 536236 (C4 (Web Text))

Max Activating Token Index: 37

Text #17

Max Range: 2.1529. Min Range: -2.1529

Max Act: 1.5493. Min Act: -0.0000

Data Index: 695695 (C4 (Web Text))

Max Activating Token Index: 768

Text #18

Max Range: 2.1529. Min Range: -2.1529

Max Act: 1.5188. Min Act: -0.0000

Data Index: 110869 (C4 (Web Text))

Max Activating Token Index: 212

Text #19

Max Range: 2.1529. Min Range: -2.1529

Max Act: 1.4354. Min Act: -0.0000

Data Index: 223263 (C4 (Web Text))

Max Activating Token Index: 347