Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4826 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0690. Min Range: -5.0690
Max Act: 5.0690. Min Act: -0.1700
Data Index: 5531771 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0690. Min Range: -5.0690
Max Act: 5.0377. Min Act: -0.1700
Data Index: 4977270 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0690. Min Range: -5.0690
Max Act: 4.9440. Min Act: -0.1700
Data Index: 2412314 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0690. Min Range: -5.0690
Max Act: 4.9752. Min Act: -0.1700
Data Index: 5772058 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0690. Min Range: -5.0690
Max Act: 4.9440. Min Act: -0.1700
Data Index: 3990593 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0690. Min Range: -5.0690
Max Act: 4.9127. Min Act: -0.1700
Data Index: 4619820 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0690. Min Range: -5.0690
Max Act: 4.8815. Min Act: -0.1700
Data Index: 1651678 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0690. Min Range: -5.0690
Max Act: 4.9127. Min Act: -0.1700
Data Index: 2345546 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0690. Min Range: -5.0690
Max Act: 4.8815. Min Act: -0.1700
Data Index: 1462471 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0690. Min Range: -5.0690
Max Act: 4.8502. Min Act: -0.1700
Data Index: 6974855 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0690. Min Range: -5.0690
Max Act: 4.8502. Min Act: -0.1700
Data Index: 2542651 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0690. Min Range: -5.0690
Max Act: 4.8502. Min Act: -0.1700
Data Index: 1124179 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0690. Min Range: -5.0690
Max Act: 4.8190. Min Act: -0.1700
Data Index: 3991638 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0690. Min Range: -5.0690
Max Act: 4.8190. Min Act: -0.1700
Data Index: 2767670 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0690. Min Range: -5.0690
Max Act: 4.8190. Min Act: -0.1700
Data Index: 457080 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0690. Min Range: -5.0690
Max Act: 4.7877. Min Act: -0.1700
Data Index: 3591059 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0690. Min Range: -5.0690
Max Act: 4.7877. Min Act: -0.1700
Data Index: 1825710 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0690. Min Range: -5.0690
Max Act: 4.7565. Min Act: -0.1700
Data Index: 3104715 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0690. Min Range: -5.0690
Max Act: 4.7877. Min Act: -0.1700
Data Index: 5098559 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0690. Min Range: -5.0690
Max Act: 4.7877. Min Act: -0.1700
Data Index: 7507684 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #19