Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3351 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.2267. Min Range: -3.2267
Max Act: 3.2267. Min Act: -0.1700
Data Index: 459678 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2267. Min Range: -3.2267
Max Act: 3.1166. Min Act: -0.1700
Data Index: 5782213 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2267. Min Range: -3.2267
Max Act: 3.0693. Min Act: -0.1700
Data Index: 1464104 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2267. Min Range: -3.2267
Max Act: 3.0377. Min Act: -0.1700
Data Index: 8347677 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2267. Min Range: -3.2267
Max Act: 3.0377. Min Act: -0.1700
Data Index: 2944126 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2267. Min Range: -3.2267
Max Act: 2.9903. Min Act: -0.1700
Data Index: 2836988 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2267. Min Range: -3.2267
Max Act: 2.9903. Min Act: -0.1700
Data Index: 6385902 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2267. Min Range: -3.2267
Max Act: 2.9903. Min Act: -0.1700
Data Index: 8007912 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2267. Min Range: -3.2267
Max Act: 2.9587. Min Act: -0.1700
Data Index: 1722438 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2267. Min Range: -3.2267
Max Act: 2.9429. Min Act: -0.1700
Data Index: 7839801 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2267. Min Range: -3.2267
Max Act: 2.9429. Min Act: -0.1700
Data Index: 8347682 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2267. Min Range: -3.2267
Max Act: 2.9270. Min Act: -0.1700
Data Index: 3305326 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2267. Min Range: -3.2267
Max Act: 2.8953. Min Act: -0.1700
Data Index: 5518293 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2267. Min Range: -3.2267
Max Act: 2.8953. Min Act: -0.1700
Data Index: 2010642 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2267. Min Range: -3.2267
Max Act: 2.8953. Min Act: -0.1700
Data Index: 210490 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2267. Min Range: -3.2267
Max Act: 2.8953. Min Act: -0.1700
Data Index: 8747334 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2267. Min Range: -3.2267
Max Act: 2.8795. Min Act: -0.1700
Data Index: 3792679 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2267. Min Range: -3.2267
Max Act: 2.8795. Min Act: -0.1700
Data Index: 8161257 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2267. Min Range: -3.2267
Max Act: 2.8795. Min Act: -0.1700
Data Index: 1849176 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2267. Min Range: -3.2267
Max Act: 2.8795. Min Act: -0.1700
Data Index: 3056068 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #19