Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2854 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6140. Min Range: -8.6140
Max Act: 8.6140. Min Act: -0.1700
Data Index: 7642243 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6140. Min Range: -8.6140
Max Act: 8.4265. Min Act: -0.1700
Data Index: 6672415 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6140. Min Range: -8.6140
Max Act: 8.3015. Min Act: -0.1700
Data Index: 3935742 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6140. Min Range: -8.6140
Max Act: 8.2390. Min Act: -0.1700
Data Index: 8389797 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6140. Min Range: -8.6140
Max Act: 8.2390. Min Act: -0.1700
Data Index: 3773282 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6140. Min Range: -8.6140
Max Act: 8.1765. Min Act: -0.1700
Data Index: 7882052 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6140. Min Range: -8.6140
Max Act: 8.1765. Min Act: -0.1700
Data Index: 6863707 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6140. Min Range: -8.6140
Max Act: 8.1140. Min Act: -0.1700
Data Index: 3143607 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6140. Min Range: -8.6140
Max Act: 8.1140. Min Act: -0.1700
Data Index: 1432797 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6140. Min Range: -8.6140
Max Act: 8.0515. Min Act: -0.1700
Data Index: 6440343 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6140. Min Range: -8.6140
Max Act: 8.0202. Min Act: -0.1700
Data Index: 500278 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6140. Min Range: -8.6140
Max Act: 8.0202. Min Act: -0.1700
Data Index: 1026477 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6140. Min Range: -8.6140
Max Act: 7.9890. Min Act: -0.1700
Data Index: 8739116 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6140. Min Range: -8.6140
Max Act: 7.9577. Min Act: -0.1700
Data Index: 4723444 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6140. Min Range: -8.6140
Max Act: 7.9265. Min Act: -0.1700
Data Index: 1548439 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6140. Min Range: -8.6140
Max Act: 7.9265. Min Act: -0.1700
Data Index: 3849673 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6140. Min Range: -8.6140
Max Act: 7.9265. Min Act: -0.1700
Data Index: 8485079 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6140. Min Range: -8.6140
Max Act: 7.9265. Min Act: -0.1700
Data Index: 4379035 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6140. Min Range: -8.6140
Max Act: 7.9265. Min Act: -0.1700
Data Index: 1409408 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6140. Min Range: -8.6140
Max Act: 7.9265. Min Act: -0.1700
Data Index: 1331808 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #19