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

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

Neuron 4914 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: 1.8502. Min Range: -1.8502

Max Act: 1.8502. Min Act: -0.0002

Data Index: 1358824 (C4 (Web Text))

Max Activating Token Index: 651

Text #1

Max Range: 1.8502. Min Range: -1.8502

Max Act: 1.6412. Min Act: -0.0002

Data Index: 795818 (C4 (Web Text))

Max Activating Token Index: 245

Text #2

Max Range: 1.8502. Min Range: -1.8502

Max Act: 1.6172. Min Act: -0.0002

Data Index: 1326783 (C4 (Web Text))

Max Activating Token Index: 195

Text #3

Max Range: 1.8502. Min Range: -1.8502

Max Act: 1.5348. Min Act: -0.0002

Data Index: 1280655 (C4 (Web Text))

Max Activating Token Index: 173

Text #4

Max Range: 1.8502. Min Range: -1.8502

Max Act: 1.4521. Min Act: -0.0002

Data Index: 1191956 (C4 (Web Text))

Max Activating Token Index: 394

Text #5

Max Range: 1.8502. Min Range: -1.8502

Max Act: 1.4412. Min Act: -0.0002

Data Index: 371570 (C4 (Web Text))

Max Activating Token Index: 191

Text #6

Max Range: 1.8502. Min Range: -1.8502

Max Act: 1.3809. Min Act: -0.0002

Data Index: 722666 (C4 (Web Text))

Max Activating Token Index: 641

Text #7

Max Range: 1.8502. Min Range: -1.8502

Max Act: 1.3489. Min Act: -0.0002

Data Index: 5261 (C4 (Web Text))

Max Activating Token Index: 605

Text #8

Max Range: 1.8502. Min Range: -1.8502

Max Act: 1.3384. Min Act: -0.0002

Data Index: 543887 (C4 (Web Text))

Max Activating Token Index: 110

Text #9

Max Range: 1.8502. Min Range: -1.8502

Max Act: 1.3314. Min Act: -0.0002

Data Index: 785140 (C4 (Web Text))

Max Activating Token Index: 304

Text #10

Max Range: 1.8502. Min Range: -1.8502

Max Act: 1.3102. Min Act: -0.0002

Data Index: 750947 (C4 (Web Text))

Max Activating Token Index: 338

Text #11

Max Range: 1.8502. Min Range: -1.8502

Max Act: 1.3029. Min Act: -0.0002

Data Index: 773838 (C4 (Web Text))

Max Activating Token Index: 176

Text #12

Max Range: 1.8502. Min Range: -1.8502

Max Act: 1.3143. Min Act: -0.0002

Data Index: 797685 (C4 (Web Text))

Max Activating Token Index: 280

Text #13

Max Range: 1.8502. Min Range: -1.8502

Max Act: 1.3393. Min Act: -0.0002

Data Index: 235181 (C4 (Web Text))

Max Activating Token Index: 166

Text #14

Max Range: 1.8502. Min Range: -1.8502

Max Act: 1.2787. Min Act: -0.0002

Data Index: 756080 (C4 (Web Text))

Max Activating Token Index: 293

Text #15

Max Range: 1.8502. Min Range: -1.8502

Max Act: 1.2875. Min Act: -0.0002

Data Index: 909849 (C4 (Web Text))

Max Activating Token Index: 221

Text #16

Max Range: 1.8502. Min Range: -1.8502

Max Act: 1.2390. Min Act: -0.0002

Data Index: 1294682 (C4 (Web Text))

Max Activating Token Index: 188

Text #17

Max Range: 1.8502. Min Range: -1.8502

Max Act: 1.2015. Min Act: -0.0002

Data Index: 1329884 (C4 (Web Text))

Max Activating Token Index: 31

Text #18

Max Range: 1.8502. Min Range: -1.8502

Max Act: 1.1838. Min Act: -0.0002

Data Index: 693296 (C4 (Web Text))

Max Activating Token Index: 298

Text #19

Max Range: 1.8502. Min Range: -1.8502

Max Act: 1.2180. Min Act: -0.0002

Data Index: 444969 (C4 (Web Text))

Max Activating Token Index: 74