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

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

Neuron 3358 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: 0.7193. Min Range: -0.7193

Max Act: 0.7193. Min Act: -0.0002

Data Index: 976571 (C4 (Web Text))

Max Activating Token Index: 275

Text #1

Max Range: 0.7193. Min Range: -0.7193

Max Act: 0.6709. Min Act: -0.0002

Data Index: 655316 (C4 (Web Text))

Max Activating Token Index: 101

Text #2

Max Range: 0.7193. Min Range: -0.7193

Max Act: 0.6603. Min Act: -0.0002

Data Index: 154088 (C4 (Web Text))

Max Activating Token Index: 774

Text #3

Max Range: 0.7193. Min Range: -0.7193

Max Act: 0.6506. Min Act: -0.0002

Data Index: 890792 (C4 (Web Text))

Max Activating Token Index: 935

Text #4

Max Range: 0.7193. Min Range: -0.7193

Max Act: 0.6320. Min Act: -0.0002

Data Index: 123994 (C4 (Web Text))

Max Activating Token Index: 5

Text #5

Max Range: 0.7193. Min Range: -0.7193

Max Act: 0.6320. Min Act: -0.0002

Data Index: 984265 (C4 (Web Text))

Max Activating Token Index: 5

Text #6

Max Range: 0.7193. Min Range: -0.7193

Max Act: 0.6504. Min Act: -0.0002

Data Index: 195056 (C4 (Web Text))

Max Activating Token Index: 152

Text #7

Max Range: 0.7193. Min Range: -0.7193

Max Act: 0.6365. Min Act: -0.0002

Data Index: 942578 (C4 (Web Text))

Max Activating Token Index: 82

Text #8

Max Range: 0.7193. Min Range: -0.7193

Max Act: 0.6486. Min Act: -0.0002

Data Index: 810109 (C4 (Web Text))

Max Activating Token Index: 918

Text #9

Max Range: 0.7193. Min Range: -0.7193

Max Act: 0.6422. Min Act: -0.0002

Data Index: 828481 (C4 (Web Text))

Max Activating Token Index: 23

Text #10

Max Range: 0.7193. Min Range: -0.7193

Max Act: 0.6202. Min Act: -0.0002

Data Index: 222291 (C4 (Web Text))

Max Activating Token Index: 46

Text #11

Max Range: 0.7193. Min Range: -0.7193

Max Act: 0.6071. Min Act: -0.0002

Data Index: 1245636 (C4 (Web Text))

Max Activating Token Index: 651

Text #12

Max Range: 0.7193. Min Range: -0.7193

Max Act: 0.6263. Min Act: -0.0002

Data Index: 1240420 (C4 (Web Text))

Max Activating Token Index: 82

Text #13

Max Range: 0.7193. Min Range: -0.7193

Max Act: 0.6226. Min Act: -0.0002

Data Index: 468585 (C4 (Web Text))

Max Activating Token Index: 497

Text #14

Max Range: 0.7193. Min Range: -0.7193

Max Act: 0.6100. Min Act: -0.0002

Data Index: 1067691 (C4 (Web Text))

Max Activating Token Index: 387

Text #15

Max Range: 0.7193. Min Range: -0.7193

Max Act: 0.6032. Min Act: -0.0002

Data Index: 901963 (C4 (Web Text))

Max Activating Token Index: 705

Text #16

Max Range: 0.7193. Min Range: -0.7193

Max Act: 0.6065. Min Act: -0.0002

Data Index: 1191106 (C4 (Web Text))

Max Activating Token Index: 849

Text #17

Max Range: 0.7193. Min Range: -0.7193

Max Act: 0.6059. Min Act: -0.0002

Data Index: 950319 (C4 (Web Text))

Max Activating Token Index: 904

Text #18

Max Range: 0.7193. Min Range: -0.7193

Max Act: 0.6122. Min Act: -0.0002

Data Index: 1206216 (C4 (Web Text))

Max Activating Token Index: 368

Text #19

Max Range: 0.7193. Min Range: -0.7193

Max Act: 0.6099. Min Act: -0.0002

Data Index: 934469 (C4 (Web Text))

Max Activating Token Index: 611