Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4018 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6011. Min Range: -4.6011
Max Act: 4.6011. Min Act: -0.1700
Data Index: 8586391 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6011. Min Range: -4.6011
Max Act: 4.3823. Min Act: -0.1700
Data Index: 6122629 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6011. Min Range: -4.6011
Max Act: 4.1948. Min Act: -0.1700
Data Index: 1460384 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6011. Min Range: -4.6011
Max Act: 4.1323. Min Act: -0.1700
Data Index: 4813878 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6011. Min Range: -4.6011
Max Act: 4.1010. Min Act: -0.1700
Data Index: 2456353 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6011. Min Range: -4.6011
Max Act: 4.1010. Min Act: -0.1700
Data Index: 6799214 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6011. Min Range: -4.6011
Max Act: 3.9760. Min Act: -0.1700
Data Index: 6050674 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6011. Min Range: -4.6011
Max Act: 4.0073. Min Act: -0.1700
Data Index: 4559263 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6011. Min Range: -4.6011
Max Act: 3.9760. Min Act: -0.1700
Data Index: 1013921 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6011. Min Range: -4.6011
Max Act: 3.9760. Min Act: -0.1700
Data Index: 999735 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6011. Min Range: -4.6011
Max Act: 3.9760. Min Act: -0.1700
Data Index: 6874133 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6011. Min Range: -4.6011
Max Act: 3.9447. Min Act: -0.1700
Data Index: 155301 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6011. Min Range: -4.6011
Max Act: 3.9447. Min Act: -0.1700
Data Index: 351882 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6011. Min Range: -4.6011
Max Act: 3.9135. Min Act: -0.1700
Data Index: 4659058 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6011. Min Range: -4.6011
Max Act: 3.9135. Min Act: -0.1700
Data Index: 1684421 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6011. Min Range: -4.6011
Max Act: 3.9135. Min Act: -0.1700
Data Index: 8070769 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6011. Min Range: -4.6011
Max Act: 3.9135. Min Act: -0.1700
Data Index: 3194651 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6011. Min Range: -4.6011
Max Act: 3.8666. Min Act: -0.1700
Data Index: 5426700 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6011. Min Range: -4.6011
Max Act: 3.8822. Min Act: -0.1700
Data Index: 8438117 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6011. Min Range: -4.6011
Max Act: 3.8509. Min Act: -0.1700
Data Index: 958511 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #19