Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3110 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9298. Min Range: -4.9298
Max Act: 4.9298. Min Act: -0.1700
Data Index: 7627208 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9298. Min Range: -4.9298
Max Act: 4.7423. Min Act: -0.1700
Data Index: 6767136 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9298. Min Range: -4.9298
Max Act: 4.7110. Min Act: -0.1700
Data Index: 3760625 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9298. Min Range: -4.9298
Max Act: 4.7110. Min Act: -0.1700
Data Index: 6423398 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9298. Min Range: -4.9298
Max Act: 4.6485. Min Act: -0.1700
Data Index: 2684378 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9298. Min Range: -4.9298
Max Act: 4.6485. Min Act: -0.1700
Data Index: 8132794 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9298. Min Range: -4.9298
Max Act: 4.6485. Min Act: -0.1700
Data Index: 2072084 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9298. Min Range: -4.9298
Max Act: 4.6173. Min Act: -0.1700
Data Index: 2268115 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9298. Min Range: -4.9298
Max Act: 4.6173. Min Act: -0.1700
Data Index: 3299932 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9298. Min Range: -4.9298
Max Act: 4.6173. Min Act: -0.1700
Data Index: 3362791 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9298. Min Range: -4.9298
Max Act: 4.6173. Min Act: -0.1700
Data Index: 7314775 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9298. Min Range: -4.9298
Max Act: 4.5548. Min Act: -0.1700
Data Index: 5014909 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9298. Min Range: -4.9298
Max Act: 4.5548. Min Act: -0.1700
Data Index: 6222905 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9298. Min Range: -4.9298
Max Act: 4.5548. Min Act: -0.1700
Data Index: 7777144 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9298. Min Range: -4.9298
Max Act: 4.5548. Min Act: -0.1700
Data Index: 2138140 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9298. Min Range: -4.9298
Max Act: 4.5548. Min Act: -0.1700
Data Index: 7527211 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9298. Min Range: -4.9298
Max Act: 4.5235. Min Act: -0.1700
Data Index: 6553341 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9298. Min Range: -4.9298
Max Act: 4.5235. Min Act: -0.1700
Data Index: 4659185 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9298. Min Range: -4.9298
Max Act: 4.5235. Min Act: -0.1700
Data Index: 2031720 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9298. Min Range: -4.9298
Max Act: 4.5235. Min Act: -0.1700
Data Index: 5233246 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #19