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

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

Neuron 5017 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: 1.9767. Min Range: -1.9767

Max Act: 1.9406. Min Act: -0.0002

Data Index: 989316 (C4 (Web Text))

Max Activating Token Index: 357

Text #1

Max Range: 1.9767. Min Range: -1.9767

Max Act: 1.8638. Min Act: -0.0002

Data Index: 1219931 (C4 (Web Text))

Max Activating Token Index: 217

Text #2

Max Range: 1.9767. Min Range: -1.9767

Max Act: 1.8828. Min Act: -0.0002

Data Index: 951353 (C4 (Web Text))

Max Activating Token Index: 247

Text #3

Max Range: 1.9767. Min Range: -1.9767

Max Act: 1.9767. Min Act: -0.0002

Data Index: 1146855 (C4 (Web Text))

Max Activating Token Index: 414

Text #4

Max Range: 1.9767. Min Range: -1.9767

Max Act: 1.8460. Min Act: -0.0002

Data Index: 486867 (C4 (Web Text))

Max Activating Token Index: 320

Text #5

Max Range: 1.9767. Min Range: -1.9767

Max Act: 1.7924. Min Act: -0.0002

Data Index: 1355251 (C4 (Web Text))

Max Activating Token Index: 251

Text #6

Max Range: 1.9767. Min Range: -1.9767

Max Act: 1.7160. Min Act: -0.0002

Data Index: 1329828 (C4 (Web Text))

Max Activating Token Index: 234

Text #7

Max Range: 1.9767. Min Range: -1.9767

Max Act: 1.7035. Min Act: -0.0002

Data Index: 41404 (C4 (Web Text))

Max Activating Token Index: 51

Text #8

Max Range: 1.9767. Min Range: -1.9767

Max Act: 1.7210. Min Act: -0.0002

Data Index: 1180346 (C4 (Web Text))

Max Activating Token Index: 287

Text #9

Max Range: 1.9767. Min Range: -1.9767

Max Act: 1.7134. Min Act: -0.0002

Data Index: 1305179 (C4 (Web Text))

Max Activating Token Index: 280

Text #10

Max Range: 1.9767. Min Range: -1.9767

Max Act: 1.6935. Min Act: -0.0002

Data Index: 895911 (C4 (Web Text))

Max Activating Token Index: 284

Text #11

Max Range: 1.9767. Min Range: -1.9767

Max Act: 1.6852. Min Act: -0.0002

Data Index: 876476 (C4 (Web Text))

Max Activating Token Index: 99

Text #12

Max Range: 1.9767. Min Range: -1.9767

Max Act: 1.6757. Min Act: -0.0002

Data Index: 445851 (C4 (Web Text))

Max Activating Token Index: 179

Text #13

Max Range: 1.9767. Min Range: -1.9767

Max Act: 1.6298. Min Act: -0.0002

Data Index: 562269 (C4 (Web Text))

Max Activating Token Index: 133

Text #14

Max Range: 1.9767. Min Range: -1.9767

Max Act: 1.6538. Min Act: -0.0002

Data Index: 758715 (C4 (Web Text))

Max Activating Token Index: 224

Text #15

Max Range: 1.9767. Min Range: -1.9767

Max Act: 1.6423. Min Act: -0.0002

Data Index: 285717 (C4 (Web Text))

Max Activating Token Index: 275

Text #16

Max Range: 1.9767. Min Range: -1.9767

Max Act: 1.7018. Min Act: -0.0002

Data Index: 1353076 (C4 (Web Text))

Max Activating Token Index: 372

Text #17

Max Range: 1.9767. Min Range: -1.9767

Max Act: 1.6303. Min Act: -0.0002

Data Index: 1309589 (C4 (Web Text))

Max Activating Token Index: 277

Text #18

Max Range: 1.9767. Min Range: -1.9767

Max Act: 1.6761. Min Act: -0.0002

Data Index: 203440 (C4 (Web Text))

Max Activating Token Index: 171

Text #19

Max Range: 1.9767. Min Range: -1.9767

Max Act: 1.6379. Min Act: -0.0002

Data Index: 509314 (C4 (Web Text))

Max Activating Token Index: 277