Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4449 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.0543. Min Range: -10.0543
Max Act: 10.0543. Min Act: -0.1700
Data Index: 3996384 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.0543. Min Range: -10.0543
Max Act: 9.2418. Min Act: -0.1700
Data Index: 3996383 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.0543. Min Range: -10.0543
Max Act: 8.2105. Min Act: -0.1700
Data Index: 1925506 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.0543. Min Range: -10.0543
Max Act: 8.1168. Min Act: -0.1700
Data Index: 1982262 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.0543. Min Range: -10.0543
Max Act: 8.1168. Min Act: -0.1700
Data Index: 3385279 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.0543. Min Range: -10.0543
Max Act: 8.0230. Min Act: -0.1700
Data Index: 2881583 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.0543. Min Range: -10.0543
Max Act: 7.9605. Min Act: -0.1700
Data Index: 2352309 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.0543. Min Range: -10.0543
Max Act: 7.8980. Min Act: -0.1700
Data Index: 3119143 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.0543. Min Range: -10.0543
Max Act: 7.8355. Min Act: -0.1700
Data Index: 863223 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.0543. Min Range: -10.0543
Max Act: 7.8668. Min Act: -0.1700
Data Index: 82007 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.0543. Min Range: -10.0543
Max Act: 7.8668. Min Act: -0.1700
Data Index: 8787176 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.0543. Min Range: -10.0543
Max Act: 7.8355. Min Act: -0.1700
Data Index: 7356712 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.0543. Min Range: -10.0543
Max Act: 7.8355. Min Act: -0.1700
Data Index: 764286 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.0543. Min Range: -10.0543
Max Act: 7.8355. Min Act: -0.1700
Data Index: 5796953 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.0543. Min Range: -10.0543
Max Act: 7.8043. Min Act: -0.1700
Data Index: 4873202 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.0543. Min Range: -10.0543
Max Act: 7.8355. Min Act: -0.1700
Data Index: 4807593 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.0543. Min Range: -10.0543
Max Act: 7.7730. Min Act: -0.1700
Data Index: 1920359 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.0543. Min Range: -10.0543
Max Act: 7.7418. Min Act: -0.1700
Data Index: 1246908 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.0543. Min Range: -10.0543
Max Act: 7.7418. Min Act: -0.1700
Data Index: 2840966 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.0543. Min Range: -10.0543
Max Act: 7.6793. Min Act: -0.1700
Data Index: 5796952 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #19