Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2265 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3893. Min Range: -5.3893
Max Act: 5.3893. Min Act: -0.1700
Data Index: 2811709 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3893. Min Range: -5.3893
Max Act: 5.1706. Min Act: -0.1700
Data Index: 4291369 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3893. Min Range: -5.3893
Max Act: 5.0143. Min Act: -0.1700
Data Index: 7430965 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3893. Min Range: -5.3893
Max Act: 4.9831. Min Act: -0.1700
Data Index: 8166006 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3893. Min Range: -5.3893
Max Act: 4.9206. Min Act: -0.1700
Data Index: 2821126 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3893. Min Range: -5.3893
Max Act: 4.9831. Min Act: -0.1700
Data Index: 2747674 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3893. Min Range: -5.3893
Max Act: 4.9518. Min Act: -0.1700
Data Index: 901060 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3893. Min Range: -5.3893
Max Act: 4.8893. Min Act: -0.1700
Data Index: 5059144 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3893. Min Range: -5.3893
Max Act: 4.9206. Min Act: -0.1700
Data Index: 7791594 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3893. Min Range: -5.3893
Max Act: 4.8581. Min Act: -0.1700
Data Index: 782269 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3893. Min Range: -5.3893
Max Act: 4.8893. Min Act: -0.1700
Data Index: 5001350 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3893. Min Range: -5.3893
Max Act: 4.8581. Min Act: -0.1700
Data Index: 8747169 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3893. Min Range: -5.3893
Max Act: 4.8268. Min Act: -0.1700
Data Index: 5059151 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3893. Min Range: -5.3893
Max Act: 4.8268. Min Act: -0.1700
Data Index: 2226378 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3893. Min Range: -5.3893
Max Act: 4.8268. Min Act: -0.1700
Data Index: 3300505 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3893. Min Range: -5.3893
Max Act: 4.7956. Min Act: -0.1700
Data Index: 7983765 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3893. Min Range: -5.3893
Max Act: 4.7956. Min Act: -0.1700
Data Index: 4204726 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3893. Min Range: -5.3893
Max Act: 4.7956. Min Act: -0.1700
Data Index: 964046 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3893. Min Range: -5.3893
Max Act: 4.7956. Min Act: -0.1700
Data Index: 4592560 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3893. Min Range: -5.3893
Max Act: 4.7643. Min Act: -0.1700
Data Index: 328423 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #19