Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3094 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1246. Min Range: -9.1246
Max Act: 9.1246. Min Act: -0.1700
Data Index: 8114871 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1246. Min Range: -9.1246
Max Act: 9.0621. Min Act: -0.1700
Data Index: 69179 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1246. Min Range: -9.1246
Max Act: 8.9996. Min Act: -0.1700
Data Index: 4241038 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1246. Min Range: -9.1246
Max Act: 8.8746. Min Act: -0.1700
Data Index: 3665565 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1246. Min Range: -9.1246
Max Act: 8.9371. Min Act: -0.1700
Data Index: 8519838 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1246. Min Range: -9.1246
Max Act: 8.9371. Min Act: -0.1700
Data Index: 4602200 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1246. Min Range: -9.1246
Max Act: 8.9371. Min Act: -0.1700
Data Index: 5707661 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1246. Min Range: -9.1246
Max Act: 8.6871. Min Act: -0.1700
Data Index: 2274063 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1246. Min Range: -9.1246
Max Act: 8.6871. Min Act: -0.1700
Data Index: 7496027 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1246. Min Range: -9.1246
Max Act: 8.6871. Min Act: -0.1700
Data Index: 1019267 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1246. Min Range: -9.1246
Max Act: 8.6246. Min Act: -0.1700
Data Index: 5285236 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1246. Min Range: -9.1246
Max Act: 8.6246. Min Act: -0.1700
Data Index: 877752 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1246. Min Range: -9.1246
Max Act: 8.6246. Min Act: -0.1700
Data Index: 426308 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1246. Min Range: -9.1246
Max Act: 8.5621. Min Act: -0.1700
Data Index: 1461081 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1246. Min Range: -9.1246
Max Act: 8.5621. Min Act: -0.1700
Data Index: 927524 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1246. Min Range: -9.1246
Max Act: 8.5621. Min Act: -0.1700
Data Index: 5435523 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1246. Min Range: -9.1246
Max Act: 8.6246. Min Act: -0.1700
Data Index: 6910221 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1246. Min Range: -9.1246
Max Act: 8.5621. Min Act: -0.1700
Data Index: 626276 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1246. Min Range: -9.1246
Max Act: 8.4996. Min Act: -0.1700
Data Index: 7668309 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1246. Min Range: -9.1246
Max Act: 8.4996. Min Act: -0.1700
Data Index: 2804995 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #19