Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 541 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 4.9579. Min Range: -4.9579
Max Act: 4.9579. Min Act: -0.1700
Data Index: 1196566 (C4 (Web Text))
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9579. Min Range: -4.9579
Max Act: 4.7704. Min Act: -0.1700
Data Index: 346339 (C4 (Web Text))
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9579. Min Range: -4.9579
Max Act: 4.7704. Min Act: -0.1700
Data Index: 395148 (C4 (Web Text))
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9579. Min Range: -4.9579
Max Act: 4.6767. Min Act: -0.1700
Data Index: 1243827 (C4 (Web Text))
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9579. Min Range: -4.9579
Max Act: 4.6454. Min Act: -0.1700
Data Index: 1046126 (C4 (Web Text))
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9579. Min Range: -4.9579
Max Act: 4.6142. Min Act: -0.1700
Data Index: 1214516 (C4 (Web Text))
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9579. Min Range: -4.9579
Max Act: 4.6454. Min Act: -0.1700
Data Index: 583659 (C4 (Web Text))
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9579. Min Range: -4.9579
Max Act: 4.5517. Min Act: -0.1700
Data Index: 1049089 (C4 (Web Text))
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9579. Min Range: -4.9579
Max Act: 4.5829. Min Act: -0.1700
Data Index: 1252931 (C4 (Web Text))
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9579. Min Range: -4.9579
Max Act: 4.5517. Min Act: -0.1700
Data Index: 842810 (C4 (Web Text))
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9579. Min Range: -4.9579
Max Act: 4.5517. Min Act: -0.1700
Data Index: 1344091 (C4 (Web Text))
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9579. Min Range: -4.9579
Max Act: 4.4892. Min Act: -0.1700
Data Index: 606564 (C4 (Web Text))
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9579. Min Range: -4.9579
Max Act: 4.5517. Min Act: -0.1700
Data Index: 77376 (C4 (Web Text))
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9579. Min Range: -4.9579
Max Act: 4.4579. Min Act: -0.1700
Data Index: 600806 (C4 (Web Text))
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9579. Min Range: -4.9579
Max Act: 4.4267. Min Act: -0.1700
Data Index: 314840 (C4 (Web Text))
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9579. Min Range: -4.9579
Max Act: 4.4267. Min Act: -0.1700
Data Index: 485801 (C4 (Web Text))
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9579. Min Range: -4.9579
Max Act: 4.4267. Min Act: -0.1700
Data Index: 499517 (C4 (Web Text))
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9579. Min Range: -4.9579
Max Act: 4.4267. Min Act: -0.1700
Data Index: 75654 (C4 (Web Text))
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9579. Min Range: -4.9579
Max Act: 4.4267. Min Act: -0.1700
Data Index: 561772 (C4 (Web Text))
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9579. Min Range: -4.9579
Max Act: 4.4579. Min Act: -0.1700
Data Index: 646737 (C4 (Web Text))
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #19