Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5541 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5646. Min Range: -7.5646
Max Act: 7.5646. Min Act: -0.1700
Data Index: 818221 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5646. Min Range: -7.5646
Max Act: 7.5333. Min Act: -0.1700
Data Index: 2342185 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5646. Min Range: -7.5646
Max Act: 7.3458. Min Act: -0.1700
Data Index: 8811473 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5646. Min Range: -7.5646
Max Act: 7.2833. Min Act: -0.1700
Data Index: 20169 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5646. Min Range: -7.5646
Max Act: 7.2833. Min Act: -0.1700
Data Index: 5748021 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5646. Min Range: -7.5646
Max Act: 7.2521. Min Act: -0.1700
Data Index: 455381 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5646. Min Range: -7.5646
Max Act: 7.2208. Min Act: -0.1700
Data Index: 7867308 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5646. Min Range: -7.5646
Max Act: 7.1896. Min Act: -0.1700
Data Index: 1182657 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5646. Min Range: -7.5646
Max Act: 7.1583. Min Act: -0.1700
Data Index: 4700826 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5646. Min Range: -7.5646
Max Act: 7.1583. Min Act: -0.1700
Data Index: 762867 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5646. Min Range: -7.5646
Max Act: 7.1271. Min Act: -0.1700
Data Index: 641522 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5646. Min Range: -7.5646
Max Act: 7.0646. Min Act: -0.1700
Data Index: 5213868 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5646. Min Range: -7.5646
Max Act: 7.0646. Min Act: -0.1700
Data Index: 6216276 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5646. Min Range: -7.5646
Max Act: 7.0333. Min Act: -0.1700
Data Index: 5671609 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5646. Min Range: -7.5646
Max Act: 7.0021. Min Act: -0.1700
Data Index: 4301630 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5646. Min Range: -7.5646
Max Act: 6.9708. Min Act: -0.1700
Data Index: 7507631 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5646. Min Range: -7.5646
Max Act: 6.9708. Min Act: -0.1700
Data Index: 6297521 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5646. Min Range: -7.5646
Max Act: 6.9396. Min Act: -0.1700
Data Index: 4040093 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5646. Min Range: -7.5646
Max Act: 6.9083. Min Act: -0.1700
Data Index: 1361574 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5646. Min Range: -7.5646
Max Act: 6.9083. Min Act: -0.1700
Data Index: 7975177 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #19