Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2032 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.2711. Min Range: -4.2711
Max Act: 4.2711. Min Act: -0.1700
Data Index: 666011 (C4 (Web Text))
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2711. Min Range: -4.2711
Max Act: 4.1461. Min Act: -0.1699
Data Index: 316304 (C4 (Web Text))
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2711. Min Range: -4.2711
Max Act: 4.1461. Min Act: -0.1700
Data Index: 102984 (C4 (Web Text))
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2711. Min Range: -4.2711
Max Act: 4.1461. Min Act: -0.1700
Data Index: 1043948 (C4 (Web Text))
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2711. Min Range: -4.2711
Max Act: 4.1461. Min Act: -0.1700
Data Index: 76888 (C4 (Web Text))
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2711. Min Range: -4.2711
Max Act: 4.1461. Min Act: -0.1700
Data Index: 100803 (C4 (Web Text))
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2711. Min Range: -4.2711
Max Act: 4.1774. Min Act: -0.1700
Data Index: 1143594 (C4 (Web Text))
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2711. Min Range: -4.2711
Max Act: 4.1149. Min Act: -0.1700
Data Index: 149301 (C4 (Web Text))
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2711. Min Range: -4.2711
Max Act: 4.1149. Min Act: -0.1699
Data Index: 689346 (C4 (Web Text))
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2711. Min Range: -4.2711
Max Act: 4.1149. Min Act: -0.1700
Data Index: 920007 (C4 (Web Text))
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2711. Min Range: -4.2711
Max Act: 4.0211. Min Act: -0.1700
Data Index: 492980 (C4 (Web Text))
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2711. Min Range: -4.2711
Max Act: 4.0523. Min Act: -0.1700
Data Index: 938604 (C4 (Web Text))
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2711. Min Range: -4.2711
Max Act: 4.1461. Min Act: -0.1700
Data Index: 312181 (C4 (Web Text))
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2711. Min Range: -4.2711
Max Act: 4.0211. Min Act: -0.1700
Data Index: 753947 (C4 (Web Text))
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2711. Min Range: -4.2711
Max Act: 4.0211. Min Act: -0.1700
Data Index: 1099395 (C4 (Web Text))
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2711. Min Range: -4.2711
Max Act: 4.0523. Min Act: -0.1700
Data Index: 1099251 (C4 (Web Text))
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2711. Min Range: -4.2711
Max Act: 4.0523. Min Act: -0.1700
Data Index: 539970 (C4 (Web Text))
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2711. Min Range: -4.2711
Max Act: 3.9898. Min Act: -0.1700
Data Index: 327816 (C4 (Web Text))
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2711. Min Range: -4.2711
Max Act: 4.0523. Min Act: -0.1700
Data Index: 1031147 (C4 (Web Text))
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2711. Min Range: -4.2711
Max Act: 3.9898. Min Act: -0.1699
Data Index: 468006 (C4 (Web Text))
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #19