Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 54 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 6.5884. Min Range: -6.5884
Max Act: 6.5571. Min Act: -0.1700
Data Index: 1004629 (C4 (Web Text))
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5884. Min Range: -6.5884
Max Act: 6.5884. Min Act: -0.1700
Data Index: 939709 (C4 (Web Text))
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5884. Min Range: -6.5884
Max Act: 6.3384. Min Act: -0.1700
Data Index: 466060 (C4 (Web Text))
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5884. Min Range: -6.5884
Max Act: 6.3696. Min Act: -0.1700
Data Index: 558433 (C4 (Web Text))
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5884. Min Range: -6.5884
Max Act: 6.2446. Min Act: -0.1700
Data Index: 202471 (C4 (Web Text))
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5884. Min Range: -6.5884
Max Act: 6.1821. Min Act: -0.1700
Data Index: 751919 (C4 (Web Text))
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5884. Min Range: -6.5884
Max Act: 6.1196. Min Act: -0.1700
Data Index: 1140521 (C4 (Web Text))
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5884. Min Range: -6.5884
Max Act: 6.1509. Min Act: -0.1700
Data Index: 642428 (C4 (Web Text))
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5884. Min Range: -6.5884
Max Act: 6.2759. Min Act: -0.1700
Data Index: 1240870 (C4 (Web Text))
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5884. Min Range: -6.5884
Max Act: 6.1509. Min Act: -0.1700
Data Index: 847134 (C4 (Web Text))
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5884. Min Range: -6.5884
Max Act: 6.1196. Min Act: -0.1700
Data Index: 965093 (C4 (Web Text))
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5884. Min Range: -6.5884
Max Act: 6.1196. Min Act: -0.1700
Data Index: 509689 (C4 (Web Text))
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5884. Min Range: -6.5884
Max Act: 6.1196. Min Act: -0.1700
Data Index: 1177497 (C4 (Web Text))
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5884. Min Range: -6.5884
Max Act: 6.0259. Min Act: -0.1700
Data Index: 328684 (C4 (Web Text))
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5884. Min Range: -6.5884
Max Act: 6.0571. Min Act: -0.1700
Data Index: 1112190 (C4 (Web Text))
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5884. Min Range: -6.5884
Max Act: 6.0259. Min Act: -0.1700
Data Index: 880130 (C4 (Web Text))
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5884. Min Range: -6.5884
Max Act: 6.0259. Min Act: -0.1700
Data Index: 769681 (C4 (Web Text))
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5884. Min Range: -6.5884
Max Act: 6.0259. Min Act: -0.1700
Data Index: 782048 (C4 (Web Text))
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5884. Min Range: -6.5884
Max Act: 5.9634. Min Act: -0.1700
Data Index: 332660 (C4 (Web Text))
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5884. Min Range: -6.5884
Max Act: 5.9946. Min Act: -0.1700
Data Index: 464401 (C4 (Web Text))
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #19