Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3098 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.2367. Min Range: -9.2367
Max Act: 9.2367. Min Act: -0.1700
Data Index: 8803418 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.2367. Min Range: -9.2367
Max Act: 9.1742. Min Act: -0.1700
Data Index: 6092190 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.2367. Min Range: -9.2367
Max Act: 9.2367. Min Act: -0.1700
Data Index: 3538297 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.2367. Min Range: -9.2367
Max Act: 9.0492. Min Act: -0.1700
Data Index: 7860789 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.2367. Min Range: -9.2367
Max Act: 9.0492. Min Act: -0.1700
Data Index: 397465 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.2367. Min Range: -9.2367
Max Act: 9.0492. Min Act: -0.1700
Data Index: 8677893 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.2367. Min Range: -9.2367
Max Act: 9.0492. Min Act: -0.1700
Data Index: 2285095 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.2367. Min Range: -9.2367
Max Act: 8.9867. Min Act: -0.1700
Data Index: 6790948 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.2367. Min Range: -9.2367
Max Act: 8.9867. Min Act: -0.1700
Data Index: 5886579 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.2367. Min Range: -9.2367
Max Act: 8.9867. Min Act: -0.1700
Data Index: 4156505 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.2367. Min Range: -9.2367
Max Act: 8.9242. Min Act: -0.1700
Data Index: 6497458 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.2367. Min Range: -9.2367
Max Act: 8.8617. Min Act: -0.1700
Data Index: 5137743 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.2367. Min Range: -9.2367
Max Act: 8.8617. Min Act: -0.1700
Data Index: 3772129 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.2367. Min Range: -9.2367
Max Act: 8.8617. Min Act: -0.1700
Data Index: 7780911 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.2367. Min Range: -9.2367
Max Act: 8.8617. Min Act: -0.1700
Data Index: 4506868 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.2367. Min Range: -9.2367
Max Act: 8.7992. Min Act: -0.1700
Data Index: 5137742 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.2367. Min Range: -9.2367
Max Act: 8.7992. Min Act: -0.1700
Data Index: 8000071 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.2367. Min Range: -9.2367
Max Act: 8.7992. Min Act: -0.1700
Data Index: 1430388 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.2367. Min Range: -9.2367
Max Act: 8.7992. Min Act: -0.1700
Data Index: 7796743 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.2367. Min Range: -9.2367
Max Act: 8.7992. Min Act: -0.1700
Data Index: 7839539 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #19