Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5822 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1497. Min Range: -5.1497
Max Act: 5.1497. Min Act: -0.1700
Data Index: 2862600 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1497. Min Range: -5.1497
Max Act: 4.7435. Min Act: -0.1700
Data Index: 4160712 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1497. Min Range: -5.1497
Max Act: 4.6810. Min Act: -0.1700
Data Index: 7299705 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1497. Min Range: -5.1497
Max Act: 4.6497. Min Act: -0.1700
Data Index: 2916025 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1497. Min Range: -5.1497
Max Act: 4.6810. Min Act: -0.1700
Data Index: 4698028 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1497. Min Range: -5.1497
Max Act: 4.6185. Min Act: -0.1700
Data Index: 7814629 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1497. Min Range: -5.1497
Max Act: 4.5872. Min Act: -0.1700
Data Index: 6118765 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1497. Min Range: -5.1497
Max Act: 4.5872. Min Act: -0.1700
Data Index: 6743274 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1497. Min Range: -5.1497
Max Act: 4.5560. Min Act: -0.1700
Data Index: 4173094 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1497. Min Range: -5.1497
Max Act: 4.5560. Min Act: -0.1700
Data Index: 7969532 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1497. Min Range: -5.1497
Max Act: 4.5560. Min Act: -0.1700
Data Index: 8009977 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1497. Min Range: -5.1497
Max Act: 4.5247. Min Act: -0.1700
Data Index: 7568301 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1497. Min Range: -5.1497
Max Act: 4.5247. Min Act: -0.1700
Data Index: 734116 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1497. Min Range: -5.1497
Max Act: 4.5247. Min Act: -0.1700
Data Index: 4675353 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1497. Min Range: -5.1497
Max Act: 4.5247. Min Act: -0.1700
Data Index: 4296438 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1497. Min Range: -5.1497
Max Act: 4.5247. Min Act: -0.1700
Data Index: 6867062 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1497. Min Range: -5.1497
Max Act: 4.4935. Min Act: -0.1700
Data Index: 4351404 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1497. Min Range: -5.1497
Max Act: 4.4935. Min Act: -0.1700
Data Index: 8446333 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1497. Min Range: -5.1497
Max Act: 4.4935. Min Act: -0.1700
Data Index: 6267514 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1497. Min Range: -5.1497
Max Act: 4.4310. Min Act: -0.1700
Data Index: 4870367 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #19