Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4087 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9194. Min Range: -6.9194
Max Act: 6.9194. Min Act: -0.1700
Data Index: 3540612 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9194. Min Range: -6.9194
Max Act: 6.8569. Min Act: -0.1700
Data Index: 21872 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9194. Min Range: -6.9194
Max Act: 6.6382. Min Act: -0.1700
Data Index: 8724340 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9194. Min Range: -6.9194
Max Act: 6.2944. Min Act: -0.1700
Data Index: 1011342 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9194. Min Range: -6.9194
Max Act: 6.3257. Min Act: -0.1700
Data Index: 4901032 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9194. Min Range: -6.9194
Max Act: 6.3569. Min Act: -0.1700
Data Index: 8603507 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9194. Min Range: -6.9194
Max Act: 6.2944. Min Act: -0.1700
Data Index: 2160387 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9194. Min Range: -6.9194
Max Act: 6.2944. Min Act: -0.1700
Data Index: 7332467 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9194. Min Range: -6.9194
Max Act: 6.2632. Min Act: -0.1700
Data Index: 2294261 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9194. Min Range: -6.9194
Max Act: 6.2632. Min Act: -0.1700
Data Index: 398284 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9194. Min Range: -6.9194
Max Act: 6.2632. Min Act: -0.1700
Data Index: 5948908 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9194. Min Range: -6.9194
Max Act: 6.2319. Min Act: -0.1700
Data Index: 6127139 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9194. Min Range: -6.9194
Max Act: 6.1694. Min Act: -0.1700
Data Index: 7725467 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9194. Min Range: -6.9194
Max Act: 6.2007. Min Act: -0.1700
Data Index: 2826899 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9194. Min Range: -6.9194
Max Act: 6.1694. Min Act: -0.1700
Data Index: 5296014 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9194. Min Range: -6.9194
Max Act: 6.1382. Min Act: -0.1700
Data Index: 6201949 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9194. Min Range: -6.9194
Max Act: 6.0444. Min Act: -0.1700
Data Index: 2173697 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9194. Min Range: -6.9194
Max Act: 6.0132. Min Act: -0.1700
Data Index: 7773861 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9194. Min Range: -6.9194
Max Act: 6.0444. Min Act: -0.1700
Data Index: 6206727 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9194. Min Range: -6.9194
Max Act: 6.0444. Min Act: -0.1700
Data Index: 3692362 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #19