Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3275 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9646. Min Range: -5.9646
Max Act: 5.9646. Min Act: -0.1700
Data Index: 7578089 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9646. Min Range: -5.9646
Max Act: 5.9333. Min Act: -0.1700
Data Index: 6303904 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9646. Min Range: -5.9646
Max Act: 5.9021. Min Act: -0.1700
Data Index: 669375 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9646. Min Range: -5.9646
Max Act: 5.8708. Min Act: -0.1700
Data Index: 8709884 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9646. Min Range: -5.9646
Max Act: 5.8708. Min Act: -0.1700
Data Index: 3743896 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9646. Min Range: -5.9646
Max Act: 5.8396. Min Act: -0.1700
Data Index: 6580013 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9646. Min Range: -5.9646
Max Act: 5.8396. Min Act: -0.1700
Data Index: 3921826 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9646. Min Range: -5.9646
Max Act: 5.8396. Min Act: -0.1700
Data Index: 8599782 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9646. Min Range: -5.9646
Max Act: 5.8396. Min Act: -0.1700
Data Index: 7798152 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9646. Min Range: -5.9646
Max Act: 5.8396. Min Act: -0.1700
Data Index: 5813693 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9646. Min Range: -5.9646
Max Act: 5.8396. Min Act: -0.1700
Data Index: 5585682 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9646. Min Range: -5.9646
Max Act: 5.8396. Min Act: -0.1700
Data Index: 7619533 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9646. Min Range: -5.9646
Max Act: 5.8396. Min Act: -0.1700
Data Index: 5179755 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9646. Min Range: -5.9646
Max Act: 5.8083. Min Act: -0.1700
Data Index: 3256303 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9646. Min Range: -5.9646
Max Act: 5.8083. Min Act: -0.1700
Data Index: 3324894 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9646. Min Range: -5.9646
Max Act: 5.8083. Min Act: -0.1700
Data Index: 3409057 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9646. Min Range: -5.9646
Max Act: 5.8083. Min Act: -0.1700
Data Index: 115039 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9646. Min Range: -5.9646
Max Act: 5.8083. Min Act: -0.1700
Data Index: 2567489 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9646. Min Range: -5.9646
Max Act: 5.8083. Min Act: -0.1700
Data Index: 7288830 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9646. Min Range: -5.9646
Max Act: 5.8083. Min Act: -0.1700
Data Index: 6839481 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #19