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

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

Neuron 4107 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: 1.6923. Min Range: -1.6923

Max Act: 1.6923. Min Act: -0.0002

Data Index: 91485 (C4 (Web Text))

Max Activating Token Index: 170

Text #1

Max Range: 1.6923. Min Range: -1.6923

Max Act: 1.6696. Min Act: -0.0002

Data Index: 1226265 (C4 (Web Text))

Max Activating Token Index: 695

Text #2

Max Range: 1.6923. Min Range: -1.6923

Max Act: 1.5754. Min Act: -0.0002

Data Index: 911875 (C4 (Web Text))

Max Activating Token Index: 974

Text #3

Max Range: 1.6923. Min Range: -1.6923

Max Act: 1.6171. Min Act: -0.0002

Data Index: 652670 (C4 (Web Text))

Max Activating Token Index: 679

Text #4

Max Range: 1.6923. Min Range: -1.6923

Max Act: 1.5339. Min Act: -0.0002

Data Index: 416002 (C4 (Web Text))

Max Activating Token Index: 704

Text #5

Max Range: 1.6923. Min Range: -1.6923

Max Act: 1.5184. Min Act: -0.0002

Data Index: 1008415 (C4 (Web Text))

Max Activating Token Index: 16

Text #6

Max Range: 1.6923. Min Range: -1.6923

Max Act: 1.4423. Min Act: -0.0002

Data Index: 455885 (C4 (Web Text))

Max Activating Token Index: 834

Text #7

Max Range: 1.6923. Min Range: -1.6923

Max Act: 1.5331. Min Act: -0.0002

Data Index: 1110837 (C4 (Web Text))

Max Activating Token Index: 47

Text #8

Max Range: 1.6923. Min Range: -1.6923

Max Act: 1.4457. Min Act: -0.0002

Data Index: 973850 (C4 (Web Text))

Max Activating Token Index: 337

Text #9

Max Range: 1.6923. Min Range: -1.6923

Max Act: 1.4980. Min Act: -0.0002

Data Index: 87097 (C4 (Web Text))

Max Activating Token Index: 513

Text #10

Max Range: 1.6923. Min Range: -1.6923

Max Act: 1.4462. Min Act: -0.0002

Data Index: 967603 (C4 (Web Text))

Max Activating Token Index: 1018

Text #11

Max Range: 1.6923. Min Range: -1.6923

Max Act: 1.4798. Min Act: -0.0002

Data Index: 396192 (C4 (Web Text))

Max Activating Token Index: 421

Text #12

Max Range: 1.6923. Min Range: -1.6923

Max Act: 1.4104. Min Act: -0.0002

Data Index: 693798 (C4 (Web Text))

Max Activating Token Index: 1008

Text #13

Max Range: 1.6923. Min Range: -1.6923

Max Act: 1.4134. Min Act: -0.0002

Data Index: 1184466 (C4 (Web Text))

Max Activating Token Index: 780

Text #14

Max Range: 1.6923. Min Range: -1.6923

Max Act: 1.4065. Min Act: -0.0002

Data Index: 1437295 (Python Code)

Max Activating Token Index: 583

Text #15

Max Range: 1.6923. Min Range: -1.6923

Max Act: 1.4457. Min Act: -0.0002

Data Index: 51755 (C4 (Web Text))

Max Activating Token Index: 300

Text #16

Max Range: 1.6923. Min Range: -1.6923

Max Act: 1.4136. Min Act: -0.0002

Data Index: 688263 (C4 (Web Text))

Max Activating Token Index: 866

Text #17

Max Range: 1.6923. Min Range: -1.6923

Max Act: 1.3738. Min Act: -0.0002

Data Index: 225793 (C4 (Web Text))

Max Activating Token Index: 193

Text #18

Max Range: 1.6923. Min Range: -1.6923

Max Act: 1.3746. Min Act: -0.0002

Data Index: 1250482 (C4 (Web Text))

Max Activating Token Index: 496

Text #19

Max Range: 1.6923. Min Range: -1.6923

Max Act: 1.3479. Min Act: -0.0002

Data Index: 1013461 (C4 (Web Text))

Max Activating Token Index: 181