Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5181 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 1.6308. Min Range: -1.6308

Max Act: 1.6308. Min Act: -0.0002

Data Index: 4719 (C4 (Web Text))

Max Activating Token Index: 392

Text #1

Max Range: 1.6308. Min Range: -1.6308

Max Act: 1.5012. Min Act: -0.0002

Data Index: 1101650 (C4 (Web Text))

Max Activating Token Index: 896

Text #2

Max Range: 1.6308. Min Range: -1.6308

Max Act: 1.5065. Min Act: -0.0002

Data Index: 196727 (C4 (Web Text))

Max Activating Token Index: 708

Text #3

Max Range: 1.6308. Min Range: -1.6308

Max Act: 1.4941. Min Act: -0.0002

Data Index: 175376 (C4 (Web Text))

Max Activating Token Index: 366

Text #4

Max Range: 1.6308. Min Range: -1.6308

Max Act: 1.4378. Min Act: -0.0002

Data Index: 191367 (C4 (Web Text))

Max Activating Token Index: 418

Text #5

Max Range: 1.6308. Min Range: -1.6308

Max Act: 1.4901. Min Act: -0.0002

Data Index: 384275 (C4 (Web Text))

Max Activating Token Index: 64

Text #6

Max Range: 1.6308. Min Range: -1.6308

Max Act: 1.4126. Min Act: -0.0002

Data Index: 343060 (C4 (Web Text))

Max Activating Token Index: 793

Text #7

Max Range: 1.6308. Min Range: -1.6308

Max Act: 1.3949. Min Act: -0.0002

Data Index: 739703 (C4 (Web Text))

Max Activating Token Index: 240

Text #8

Max Range: 1.6308. Min Range: -1.6308

Max Act: 1.3759. Min Act: -0.0002

Data Index: 901551 (C4 (Web Text))

Max Activating Token Index: 905

Text #9

Max Range: 1.6308. Min Range: -1.6308

Max Act: 1.4559. Min Act: -0.0002

Data Index: 1111831 (C4 (Web Text))

Max Activating Token Index: 376

Text #10

Max Range: 1.6308. Min Range: -1.6308

Max Act: 1.3910. Min Act: -0.0002

Data Index: 204370 (C4 (Web Text))

Max Activating Token Index: 820

Text #11

Max Range: 1.6308. Min Range: -1.6308

Max Act: 1.3487. Min Act: -0.0002

Data Index: 1000762 (C4 (Web Text))

Max Activating Token Index: 212

Text #12

Max Range: 1.6308. Min Range: -1.6308

Max Act: 1.4263. Min Act: -0.0002

Data Index: 828818 (C4 (Web Text))

Max Activating Token Index: 124

Text #13

Max Range: 1.6308. Min Range: -1.6308

Max Act: 1.3949. Min Act: -0.0002

Data Index: 934567 (C4 (Web Text))

Max Activating Token Index: 713

Text #14

Max Range: 1.6308. Min Range: -1.6308

Max Act: 1.3781. Min Act: -0.0002

Data Index: 576346 (C4 (Web Text))

Max Activating Token Index: 310

Text #15

Max Range: 1.6308. Min Range: -1.6308

Max Act: 1.3379. Min Act: -0.0002

Data Index: 1009041 (C4 (Web Text))

Max Activating Token Index: 667

Text #16

Max Range: 1.6308. Min Range: -1.6308

Max Act: 1.3925. Min Act: -0.0002

Data Index: 728248 (C4 (Web Text))

Max Activating Token Index: 670

Text #17

Max Range: 1.6308. Min Range: -1.6308

Max Act: 1.3474. Min Act: -0.0002

Data Index: 294691 (C4 (Web Text))

Max Activating Token Index: 83

Text #18

Max Range: 1.6308. Min Range: -1.6308

Max Act: 1.3515. Min Act: -0.0002

Data Index: 81916 (C4 (Web Text))

Max Activating Token Index: 514

Text #19

Max Range: 1.6308. Min Range: -1.6308

Max Act: 1.3873. Min Act: -0.0002

Data Index: 1198201 (C4 (Web Text))

Max Activating Token Index: 669