Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4931 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.9716. Min Range: -2.9716
Max Act: 2.9716. Min Act: -0.1700
Data Index: 8762950 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9716. Min Range: -2.9716
Max Act: 2.8606. Min Act: -0.1699
Data Index: 7720216 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9716. Min Range: -2.9716
Max Act: 2.8447. Min Act: -0.1700
Data Index: 585239 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9716. Min Range: -2.9716
Max Act: 2.8288. Min Act: -0.1700
Data Index: 6481912 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9716. Min Range: -2.9716
Max Act: 2.8288. Min Act: -0.1700
Data Index: 1214531 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9716. Min Range: -2.9716
Max Act: 2.8288. Min Act: -0.1700
Data Index: 7518150 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9716. Min Range: -2.9716
Max Act: 2.8288. Min Act: -0.1700
Data Index: 883181 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9716. Min Range: -2.9716
Max Act: 2.8129. Min Act: -0.1700
Data Index: 7116406 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9716. Min Range: -2.9716
Max Act: 2.8288. Min Act: -0.1700
Data Index: 7247988 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9716. Min Range: -2.9716
Max Act: 2.8129. Min Act: -0.1700
Data Index: 6414040 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9716. Min Range: -2.9716
Max Act: 2.8129. Min Act: -0.1700
Data Index: 2179580 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9716. Min Range: -2.9716
Max Act: 2.7970. Min Act: -0.1700
Data Index: 2316704 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9716. Min Range: -2.9716
Max Act: 2.7811. Min Act: -0.1700
Data Index: 924045 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9716. Min Range: -2.9716
Max Act: 2.7970. Min Act: -0.1700
Data Index: 1012281 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9716. Min Range: -2.9716
Max Act: 2.7970. Min Act: -0.1700
Data Index: 8284298 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9716. Min Range: -2.9716
Max Act: 2.7811. Min Act: -0.1700
Data Index: 6725997 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9716. Min Range: -2.9716
Max Act: 2.7811. Min Act: -0.1700
Data Index: 6863443 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9716. Min Range: -2.9716
Max Act: 2.7970. Min Act: -0.1700
Data Index: 1740556 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9716. Min Range: -2.9716
Max Act: 2.7811. Min Act: -0.1700
Data Index: 1852771 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9716. Min Range: -2.9716
Max Act: 2.7970. Min Act: -0.1700
Data Index: 929243 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #19