Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1508 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.7542. Min Range: -12.7542
Max Act: 12.7542. Min Act: -0.1700
Data Index: 7172044 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.7542. Min Range: -12.7542
Max Act: 12.6917. Min Act: -0.1700
Data Index: 131759 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.7542. Min Range: -12.7542
Max Act: 12.6917. Min Act: -0.1700
Data Index: 2349695 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.7542. Min Range: -12.7542
Max Act: 12.6917. Min Act: -0.1700
Data Index: 841991 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.7542. Min Range: -12.7542
Max Act: 12.6917. Min Act: -0.1700
Data Index: 5846480 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.7542. Min Range: -12.7542
Max Act: 12.6917. Min Act: -0.1700
Data Index: 6486465 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.7542. Min Range: -12.7542
Max Act: 12.6917. Min Act: -0.1700
Data Index: 2002961 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.7542. Min Range: -12.7542
Max Act: 12.6917. Min Act: -0.1700
Data Index: 3470379 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.7542. Min Range: -12.7542
Max Act: 12.6917. Min Act: -0.1700
Data Index: 4553865 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.7542. Min Range: -12.7542
Max Act: 12.6917. Min Act: -0.1700
Data Index: 3633268 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.7542. Min Range: -12.7542
Max Act: 12.6292. Min Act: -0.1700
Data Index: 4755166 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.7542. Min Range: -12.7542
Max Act: 12.6292. Min Act: -0.1700
Data Index: 4652514 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.7542. Min Range: -12.7542
Max Act: 12.6292. Min Act: -0.1700
Data Index: 4353528 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.7542. Min Range: -12.7542
Max Act: 12.6292. Min Act: -0.1700
Data Index: 3872564 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.7542. Min Range: -12.7542
Max Act: 12.6292. Min Act: -0.1700
Data Index: 3587218 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.7542. Min Range: -12.7542
Max Act: 12.5667. Min Act: -0.1700
Data Index: 1282532 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.7542. Min Range: -12.7542
Max Act: 12.6292. Min Act: -0.1700
Data Index: 3580751 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.7542. Min Range: -12.7542
Max Act: 12.6292. Min Act: -0.1700
Data Index: 3555166 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.7542. Min Range: -12.7542
Max Act: 12.6292. Min Act: -0.1700
Data Index: 1128149 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.7542. Min Range: -12.7542
Max Act: 12.6292. Min Act: -0.1700
Data Index: 991019 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #19