Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3682 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3065. Min Range: -5.3065
Max Act: 5.3065. Min Act: -0.1700
Data Index: 7882332 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3065. Min Range: -5.3065
Max Act: 5.0252. Min Act: -0.1700
Data Index: 1263509 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3065. Min Range: -5.3065
Max Act: 4.9940. Min Act: -0.1700
Data Index: 3535164 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3065. Min Range: -5.3065
Max Act: 4.9940. Min Act: -0.1700
Data Index: 2938384 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3065. Min Range: -5.3065
Max Act: 5.0252. Min Act: -0.1700
Data Index: 1211068 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3065. Min Range: -5.3065
Max Act: 4.9627. Min Act: -0.1700
Data Index: 6505149 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3065. Min Range: -5.3065
Max Act: 4.9627. Min Act: -0.1700
Data Index: 3458436 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3065. Min Range: -5.3065
Max Act: 4.9315. Min Act: -0.1700
Data Index: 6105693 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3065. Min Range: -5.3065
Max Act: 4.9315. Min Act: -0.1700
Data Index: 6512882 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3065. Min Range: -5.3065
Max Act: 4.9002. Min Act: -0.1700
Data Index: 5014841 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3065. Min Range: -5.3065
Max Act: 4.9002. Min Act: -0.1700
Data Index: 1568701 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3065. Min Range: -5.3065
Max Act: 4.9315. Min Act: -0.1700
Data Index: 8702902 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3065. Min Range: -5.3065
Max Act: 4.9002. Min Act: -0.1700
Data Index: 8176503 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3065. Min Range: -5.3065
Max Act: 4.8690. Min Act: -0.1700
Data Index: 3165804 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3065. Min Range: -5.3065
Max Act: 4.8690. Min Act: -0.1700
Data Index: 7184321 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3065. Min Range: -5.3065
Max Act: 4.8690. Min Act: -0.1700
Data Index: 677351 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3065. Min Range: -5.3065
Max Act: 4.8377. Min Act: -0.1700
Data Index: 4125616 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3065. Min Range: -5.3065
Max Act: 4.8377. Min Act: -0.1700
Data Index: 3186784 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3065. Min Range: -5.3065
Max Act: 4.8377. Min Act: -0.1700
Data Index: 753467 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3065. Min Range: -5.3065
Max Act: 4.8377. Min Act: -0.1700
Data Index: 836857 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #19