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

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

Neuron 6038 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: 0.6441. Min Range: -0.6441

Max Act: 0.6441. Min Act: -0.0002

Data Index: 1089521 (C4 (Web Text))

Max Activating Token Index: 738

Text #1

Max Range: 0.6441. Min Range: -0.6441

Max Act: 0.6129. Min Act: -0.0002

Data Index: 1520655 (Python Code)

Max Activating Token Index: 251

Text #2

Max Range: 0.6441. Min Range: -0.6441

Max Act: 0.5756. Min Act: -0.0002

Data Index: 911733 (C4 (Web Text))

Max Activating Token Index: 751

Text #3

Max Range: 0.6441. Min Range: -0.6441

Max Act: 0.5905. Min Act: -0.0002

Data Index: 193567 (C4 (Web Text))

Max Activating Token Index: 739

Text #4

Max Range: 0.6441. Min Range: -0.6441

Max Act: 0.5670. Min Act: -0.0002

Data Index: 2996 (C4 (Web Text))

Max Activating Token Index: 210

Text #5

Max Range: 0.6441. Min Range: -0.6441

Max Act: 0.5754. Min Act: -0.0002

Data Index: 1279846 (C4 (Web Text))

Max Activating Token Index: 58

Text #6

Max Range: 0.6441. Min Range: -0.6441

Max Act: 0.5710. Min Act: -0.0002

Data Index: 684028 (C4 (Web Text))

Max Activating Token Index: 8

Text #7

Max Range: 0.6441. Min Range: -0.6441

Max Act: 0.5565. Min Act: -0.0002

Data Index: 370279 (C4 (Web Text))

Max Activating Token Index: 3

Text #8

Max Range: 0.6441. Min Range: -0.6441

Max Act: 0.5626. Min Act: -0.0002

Data Index: 100350 (C4 (Web Text))

Max Activating Token Index: 49

Text #9

Max Range: 0.6441. Min Range: -0.6441

Max Act: 0.5638. Min Act: -0.0002

Data Index: 55443 (C4 (Web Text))

Max Activating Token Index: 484

Text #10

Max Range: 0.6441. Min Range: -0.6441

Max Act: 0.5583. Min Act: -0.0002

Data Index: 668977 (C4 (Web Text))

Max Activating Token Index: 770

Text #11

Max Range: 0.6441. Min Range: -0.6441

Max Act: 0.5592. Min Act: -0.0002

Data Index: 1397916 (Python Code)

Max Activating Token Index: 224

Text #12

Max Range: 0.6441. Min Range: -0.6441

Max Act: 0.5554. Min Act: -0.0002

Data Index: 112385 (C4 (Web Text))

Max Activating Token Index: 665

Text #13

Max Range: 0.6441. Min Range: -0.6441

Max Act: 0.5517. Min Act: -0.0002

Data Index: 1468599 (Python Code)

Max Activating Token Index: 191

Text #14

Max Range: 0.6441. Min Range: -0.6441

Max Act: 0.5502. Min Act: -0.0002

Data Index: 499265 (C4 (Web Text))

Max Activating Token Index: 10

Text #15

Max Range: 0.6441. Min Range: -0.6441

Max Act: 0.5456. Min Act: -0.0002

Data Index: 1065788 (C4 (Web Text))

Max Activating Token Index: 285

Text #16

Max Range: 0.6441. Min Range: -0.6441

Max Act: 0.5480. Min Act: -0.0002

Data Index: 1196236 (C4 (Web Text))

Max Activating Token Index: 629

Text #17

Max Range: 0.6441. Min Range: -0.6441

Max Act: 0.5448. Min Act: -0.0002

Data Index: 392160 (C4 (Web Text))

Max Activating Token Index: 801

Text #18

Max Range: 0.6441. Min Range: -0.6441

Max Act: 0.5370. Min Act: -0.0002

Data Index: 669377 (C4 (Web Text))

Max Activating Token Index: 609

Text #19

Max Range: 0.6441. Min Range: -0.6441

Max Act: 0.5462. Min Act: -0.0002

Data Index: 1039868 (C4 (Web Text))

Max Activating Token Index: 875