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

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

Neuron 3964 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: 3.0372. Min Range: -3.0372

Max Act: 3.0372. Min Act: -0.0003

Data Index: 1110749 (C4 (Web Text))

Max Activating Token Index: 526

Text #1

Max Range: 3.0372. Min Range: -3.0372

Max Act: 3.0060. Min Act: -0.0002

Data Index: 225150 (C4 (Web Text))

Max Activating Token Index: 99

Text #2

Max Range: 3.0372. Min Range: -3.0372

Max Act: 3.0219. Min Act: -0.0002

Data Index: 498524 (C4 (Web Text))

Max Activating Token Index: 63

Text #3

Max Range: 3.0372. Min Range: -3.0372

Max Act: 3.0006. Min Act: -0.0002

Data Index: 411745 (C4 (Web Text))

Max Activating Token Index: 665

Text #4

Max Range: 3.0372. Min Range: -3.0372

Max Act: 2.9609. Min Act: -0.0002

Data Index: 142833 (C4 (Web Text))

Max Activating Token Index: 827

Text #5

Max Range: 3.0372. Min Range: -3.0372

Max Act: 3.0306. Min Act: -0.0003

Data Index: 1258033 (C4 (Web Text))

Max Activating Token Index: 790

Text #6

Max Range: 3.0372. Min Range: -3.0372

Max Act: 2.8953. Min Act: -0.0002

Data Index: 357598 (C4 (Web Text))

Max Activating Token Index: 333

Text #7

Max Range: 3.0372. Min Range: -3.0372

Max Act: 2.8120. Min Act: -0.0002

Data Index: 898934 (C4 (Web Text))

Max Activating Token Index: 415

Text #8

Max Range: 3.0372. Min Range: -3.0372

Max Act: 2.8234. Min Act: -0.0002

Data Index: 268493 (C4 (Web Text))

Max Activating Token Index: 263

Text #9

Max Range: 3.0372. Min Range: -3.0372

Max Act: 2.7732. Min Act: -0.0002

Data Index: 348646 (C4 (Web Text))

Max Activating Token Index: 741

Text #10

Max Range: 3.0372. Min Range: -3.0372

Max Act: 2.8132. Min Act: -0.0002

Data Index: 446250 (C4 (Web Text))

Max Activating Token Index: 550

Text #11

Max Range: 3.0372. Min Range: -3.0372

Max Act: 2.7086. Min Act: -0.0002

Data Index: 1040604 (C4 (Web Text))

Max Activating Token Index: 32

Text #12

Max Range: 3.0372. Min Range: -3.0372

Max Act: 2.7267. Min Act: -0.0002

Data Index: 266273 (C4 (Web Text))

Max Activating Token Index: 333

Text #13

Max Range: 3.0372. Min Range: -3.0372

Max Act: 2.7087. Min Act: -0.0002

Data Index: 1279290 (C4 (Web Text))

Max Activating Token Index: 467

Text #14

Max Range: 3.0372. Min Range: -3.0372

Max Act: 2.6901. Min Act: -0.0002

Data Index: 1144964 (C4 (Web Text))

Max Activating Token Index: 314

Text #15

Max Range: 3.0372. Min Range: -3.0372

Max Act: 2.7036. Min Act: -0.0002

Data Index: 612831 (C4 (Web Text))

Max Activating Token Index: 12

Text #16

Max Range: 3.0372. Min Range: -3.0372

Max Act: 2.7073. Min Act: -0.0002

Data Index: 1005875 (C4 (Web Text))

Max Activating Token Index: 671

Text #17

Max Range: 3.0372. Min Range: -3.0372

Max Act: 2.6727. Min Act: -0.0002

Data Index: 497406 (C4 (Web Text))

Max Activating Token Index: 664

Text #18

Max Range: 3.0372. Min Range: -3.0372

Max Act: 2.6548. Min Act: -0.0002

Data Index: 158934 (C4 (Web Text))

Max Activating Token Index: 403

Text #19

Max Range: 3.0372. Min Range: -3.0372

Max Act: 2.6257. Min Act: -0.0002

Data Index: 1267453 (C4 (Web Text))

Max Activating Token Index: 941