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

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

Neuron 5498 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: 0.5708. Min Range: -0.5708

Max Act: 0.5708. Min Act: -0.0002

Data Index: 370809 (C4 (Web Text))

Max Activating Token Index: 66

Text #1

Max Range: 0.5708. Min Range: -0.5708

Max Act: 0.5431. Min Act: -0.0002

Data Index: 4626 (C4 (Web Text))

Max Activating Token Index: 322

Text #2

Max Range: 0.5708. Min Range: -0.5708

Max Act: 0.5383. Min Act: -0.0002

Data Index: 477974 (C4 (Web Text))

Max Activating Token Index: 291

Text #3

Max Range: 0.5708. Min Range: -0.5708

Max Act: 0.5297. Min Act: -0.0002

Data Index: 623340 (C4 (Web Text))

Max Activating Token Index: 781

Text #4

Max Range: 0.5708. Min Range: -0.5708

Max Act: 0.5079. Min Act: -0.0003

Data Index: 599820 (C4 (Web Text))

Max Activating Token Index: 191

Text #5

Max Range: 0.5708. Min Range: -0.5708

Max Act: 0.4962. Min Act: -0.0002

Data Index: 3930 (C4 (Web Text))

Max Activating Token Index: 454

Text #6

Max Range: 0.5708. Min Range: -0.5708

Max Act: 0.4808. Min Act: -0.0002

Data Index: 711556 (C4 (Web Text))

Max Activating Token Index: 345

Text #7

Max Range: 0.5708. Min Range: -0.5708

Max Act: 0.4873. Min Act: -0.0002

Data Index: 354045 (C4 (Web Text))

Max Activating Token Index: 713

Text #8

Max Range: 0.5708. Min Range: -0.5708

Max Act: 0.4808. Min Act: -0.0002

Data Index: 1344918 (C4 (Web Text))

Max Activating Token Index: 283

Text #9

Max Range: 0.5708. Min Range: -0.5708

Max Act: 0.4727. Min Act: -0.0002

Data Index: 1213303 (C4 (Web Text))

Max Activating Token Index: 141

Text #10

Max Range: 0.5708. Min Range: -0.5708

Max Act: 0.4657. Min Act: -0.0002

Data Index: 277323 (C4 (Web Text))

Max Activating Token Index: 181

Text #11

Max Range: 0.5708. Min Range: -0.5708

Max Act: 0.4542. Min Act: -0.0002

Data Index: 563552 (C4 (Web Text))

Max Activating Token Index: 107

Text #12

Max Range: 0.5708. Min Range: -0.5708

Max Act: 0.4485. Min Act: -0.0002

Data Index: 227243 (C4 (Web Text))

Max Activating Token Index: 311

Text #13

Max Range: 0.5708. Min Range: -0.5708

Max Act: 0.4368. Min Act: -0.0002

Data Index: 300146 (C4 (Web Text))

Max Activating Token Index: 209

Text #14

Max Range: 0.5708. Min Range: -0.5708

Max Act: 0.4378. Min Act: -0.0002

Data Index: 1183148 (C4 (Web Text))

Max Activating Token Index: 762

Text #15

Max Range: 0.5708. Min Range: -0.5708

Max Act: 0.4329. Min Act: -0.0002

Data Index: 1306793 (C4 (Web Text))

Max Activating Token Index: 314

Text #16

Max Range: 0.5708. Min Range: -0.5708

Max Act: 0.4149. Min Act: -0.0002

Data Index: 1127046 (C4 (Web Text))

Max Activating Token Index: 816

Text #17

Max Range: 0.5708. Min Range: -0.5708

Max Act: 0.4263. Min Act: -0.0002

Data Index: 930227 (C4 (Web Text))

Max Activating Token Index: 935

Text #18

Max Range: 0.5708. Min Range: -0.5708

Max Act: 0.4137. Min Act: -0.0002

Data Index: 289033 (C4 (Web Text))

Max Activating Token Index: 943

Text #19

Max Range: 0.5708. Min Range: -0.5708

Max Act: 0.4065. Min Act: -0.0002

Data Index: 1341016 (C4 (Web Text))

Max Activating Token Index: 489