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

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

Neuron 3928 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: 2.3591. Min Range: -2.3591

Max Act: 2.3591. Min Act: -0.0002

Data Index: 1085596 (C4 (Web Text))

Max Activating Token Index: 294

Text #1

Max Range: 2.3591. Min Range: -2.3591

Max Act: 1.9758. Min Act: -0.0002

Data Index: 93755 (C4 (Web Text))

Max Activating Token Index: 253

Text #2

Max Range: 2.3591. Min Range: -2.3591

Max Act: 1.9231. Min Act: -0.0002

Data Index: 960609 (C4 (Web Text))

Max Activating Token Index: 455

Text #3

Max Range: 2.3591. Min Range: -2.3591

Max Act: 1.9437. Min Act: -0.0002

Data Index: 193956 (C4 (Web Text))

Max Activating Token Index: 433

Text #4

Max Range: 2.3591. Min Range: -2.3591

Max Act: 1.9290. Min Act: -0.0002

Data Index: 960645 (C4 (Web Text))

Max Activating Token Index: 678

Text #5

Max Range: 2.3591. Min Range: -2.3591

Max Act: 1.9040. Min Act: -0.0002

Data Index: 1291830 (C4 (Web Text))

Max Activating Token Index: 17

Text #6

Max Range: 2.3591. Min Range: -2.3591

Max Act: 1.8658. Min Act: -0.0002

Data Index: 776801 (C4 (Web Text))

Max Activating Token Index: 628

Text #7

Max Range: 2.3591. Min Range: -2.3591

Max Act: 1.8384. Min Act: -0.0002

Data Index: 497587 (C4 (Web Text))

Max Activating Token Index: 363

Text #8

Max Range: 2.3591. Min Range: -2.3591

Max Act: 1.7818. Min Act: -0.0002

Data Index: 600194 (C4 (Web Text))

Max Activating Token Index: 610

Text #9

Max Range: 2.3591. Min Range: -2.3591

Max Act: 1.7767. Min Act: -0.0002

Data Index: 827703 (C4 (Web Text))

Max Activating Token Index: 742

Text #10

Max Range: 2.3591. Min Range: -2.3591

Max Act: 1.7597. Min Act: -0.0002

Data Index: 986201 (C4 (Web Text))

Max Activating Token Index: 774

Text #11

Max Range: 2.3591. Min Range: -2.3591

Max Act: 1.8054. Min Act: -0.0002

Data Index: 342631 (C4 (Web Text))

Max Activating Token Index: 120

Text #12

Max Range: 2.3591. Min Range: -2.3591

Max Act: 1.8115. Min Act: -0.0002

Data Index: 871592 (C4 (Web Text))

Max Activating Token Index: 657

Text #13

Max Range: 2.3591. Min Range: -2.3591

Max Act: 1.7633. Min Act: -0.0002

Data Index: 526957 (C4 (Web Text))

Max Activating Token Index: 734

Text #14

Max Range: 2.3591. Min Range: -2.3591

Max Act: 1.7717. Min Act: -0.0002

Data Index: 800747 (C4 (Web Text))

Max Activating Token Index: 738

Text #15

Max Range: 2.3591. Min Range: -2.3591

Max Act: 1.7381. Min Act: -0.0002

Data Index: 979123 (C4 (Web Text))

Max Activating Token Index: 694

Text #16

Max Range: 2.3591. Min Range: -2.3591

Max Act: 1.6656. Min Act: -0.0002

Data Index: 745745 (C4 (Web Text))

Max Activating Token Index: 57

Text #17

Max Range: 2.3591. Min Range: -2.3591

Max Act: 1.7200. Min Act: -0.0002

Data Index: 231366 (C4 (Web Text))

Max Activating Token Index: 936

Text #18

Max Range: 2.3591. Min Range: -2.3591

Max Act: 1.6991. Min Act: -0.0002

Data Index: 328293 (C4 (Web Text))

Max Activating Token Index: 819

Text #19

Max Range: 2.3591. Min Range: -2.3591

Max Act: 1.7455. Min Act: -0.0002

Data Index: 122979 (C4 (Web Text))

Max Activating Token Index: 774