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

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

Neuron 2235 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0540. Min Act: -0.0002

Data Index: 721844 (C4 (Web Text))

Max Activating Token Index: 587

Text #1

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0491. Min Act: -0.0002

Data Index: 55326 (C4 (Web Text))

Max Activating Token Index: 194

Text #2

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0433. Min Act: -0.0002

Data Index: 230 (C4 (Web Text))

Max Activating Token Index: 99

Text #3

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0435. Min Act: -0.0002

Data Index: 578464 (C4 (Web Text))

Max Activating Token Index: 804

Text #4

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0379. Min Act: -0.0002

Data Index: 293674 (C4 (Web Text))

Max Activating Token Index: 528

Text #5

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0387. Min Act: -0.0002

Data Index: 946565 (C4 (Web Text))

Max Activating Token Index: 160

Text #6

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0373. Min Act: -0.0002

Data Index: 795990 (C4 (Web Text))

Max Activating Token Index: 381

Text #7

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0375. Min Act: -0.0002

Data Index: 154280 (C4 (Web Text))

Max Activating Token Index: 179

Text #8

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0362. Min Act: -0.0002

Data Index: 872608 (C4 (Web Text))

Max Activating Token Index: 447

Text #9

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0371. Min Act: -0.0002

Data Index: 59063 (C4 (Web Text))

Max Activating Token Index: 469

Text #10

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0355. Min Act: -0.0002

Data Index: 951705 (C4 (Web Text))

Max Activating Token Index: 210

Text #11

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0345. Min Act: -0.0002

Data Index: 1196288 (C4 (Web Text))

Max Activating Token Index: 796

Text #12

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0372. Min Act: -0.0002

Data Index: 1311055 (C4 (Web Text))

Max Activating Token Index: 953

Text #13

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0362. Min Act: -0.0002

Data Index: 1152493 (C4 (Web Text))

Max Activating Token Index: 86

Text #14

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0358. Min Act: -0.0002

Data Index: 61896 (C4 (Web Text))

Max Activating Token Index: 473

Text #15

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0379. Min Act: -0.0002

Data Index: 951710 (C4 (Web Text))

Max Activating Token Index: 417

Text #16

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0343. Min Act: -0.0002

Data Index: 554315 (C4 (Web Text))

Max Activating Token Index: 20

Text #17

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0350. Min Act: -0.0002

Data Index: 198237 (C4 (Web Text))

Max Activating Token Index: 189

Text #18

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0334. Min Act: -0.0002

Data Index: 1016400 (C4 (Web Text))

Max Activating Token Index: 776

Text #19

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0357. Min Act: -0.0002

Data Index: 307085 (C4 (Web Text))

Max Activating Token Index: 153