Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 10 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3587. Min Range: -6.3587
Max Act: 6.3587. Min Act: -0.1700
Data Index: 7446453 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3587. Min Range: -6.3587
Max Act: 6.2025. Min Act: -0.1700
Data Index: 1088000 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3587. Min Range: -6.3587
Max Act: 6.0150. Min Act: -0.1700
Data Index: 2231822 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3587. Min Range: -6.3587
Max Act: 5.9212. Min Act: -0.1700
Data Index: 5773947 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3587. Min Range: -6.3587
Max Act: 5.8900. Min Act: -0.1700
Data Index: 5016461 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3587. Min Range: -6.3587
Max Act: 5.8900. Min Act: -0.1700
Data Index: 7171907 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3587. Min Range: -6.3587
Max Act: 5.8900. Min Act: -0.1700
Data Index: 7962548 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3587. Min Range: -6.3587
Max Act: 5.8587. Min Act: -0.1700
Data Index: 4416912 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3587. Min Range: -6.3587
Max Act: 5.7962. Min Act: -0.1700
Data Index: 821234 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3587. Min Range: -6.3587
Max Act: 5.7962. Min Act: -0.1700
Data Index: 1096174 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3587. Min Range: -6.3587
Max Act: 5.7962. Min Act: -0.1700
Data Index: 7036648 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3587. Min Range: -6.3587
Max Act: 5.7650. Min Act: -0.1700
Data Index: 606335 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3587. Min Range: -6.3587
Max Act: 5.7650. Min Act: -0.1700
Data Index: 3776391 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3587. Min Range: -6.3587
Max Act: 5.7025. Min Act: -0.1700
Data Index: 8686326 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3587. Min Range: -6.3587
Max Act: 5.7337. Min Act: -0.1700
Data Index: 8550474 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3587. Min Range: -6.3587
Max Act: 5.7337. Min Act: -0.1700
Data Index: 8704077 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3587. Min Range: -6.3587
Max Act: 5.7025. Min Act: -0.1700
Data Index: 7549501 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3587. Min Range: -6.3587
Max Act: 5.7337. Min Act: -0.1700
Data Index: 7785938 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3587. Min Range: -6.3587
Max Act: 5.6712. Min Act: -0.1700
Data Index: 8406220 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3587. Min Range: -6.3587
Max Act: 5.7025. Min Act: -0.1700
Data Index: 4608527 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #19