Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3283 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2690. Min Range: -4.2690
Max Act: 4.2690. Min Act: -0.1700
Data Index: 3014862 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2690. Min Range: -4.2690
Max Act: 4.2377. Min Act: -0.1700
Data Index: 7559542 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2690. Min Range: -4.2690
Max Act: 4.2065. Min Act: -0.1700
Data Index: 2374012 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2690. Min Range: -4.2690
Max Act: 4.1752. Min Act: -0.1700
Data Index: 6329429 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2690. Min Range: -4.2690
Max Act: 4.1752. Min Act: -0.1700
Data Index: 8645030 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2690. Min Range: -4.2690
Max Act: 4.1440. Min Act: -0.1700
Data Index: 5008027 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2690. Min Range: -4.2690
Max Act: 4.1440. Min Act: -0.1700
Data Index: 3616914 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2690. Min Range: -4.2690
Max Act: 4.1440. Min Act: -0.1700
Data Index: 4634309 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2690. Min Range: -4.2690
Max Act: 4.1127. Min Act: -0.1700
Data Index: 5058342 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2690. Min Range: -4.2690
Max Act: 4.0815. Min Act: -0.1700
Data Index: 909132 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2690. Min Range: -4.2690
Max Act: 4.0502. Min Act: -0.1700
Data Index: 3415779 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2690. Min Range: -4.2690
Max Act: 4.0815. Min Act: -0.1700
Data Index: 6851894 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2690. Min Range: -4.2690
Max Act: 4.0815. Min Act: -0.1700
Data Index: 5008023 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2690. Min Range: -4.2690
Max Act: 4.1127. Min Act: -0.1700
Data Index: 2672999 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2690. Min Range: -4.2690
Max Act: 4.0502. Min Act: -0.1700
Data Index: 8048757 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2690. Min Range: -4.2690
Max Act: 4.0815. Min Act: -0.1700
Data Index: 5008026 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2690. Min Range: -4.2690
Max Act: 4.0502. Min Act: -0.1700
Data Index: 1951888 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2690. Min Range: -4.2690
Max Act: 4.0502. Min Act: -0.1700
Data Index: 529253 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2690. Min Range: -4.2690
Max Act: 4.0189. Min Act: -0.1700
Data Index: 5008011 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2690. Min Range: -4.2690
Max Act: 4.0189. Min Act: -0.1700
Data Index: 6810301 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #19