Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2664 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7730. Min Range: -3.7730
Max Act: 3.7730. Min Act: -0.1700
Data Index: 2772471 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7730. Min Range: -3.7730
Max Act: 3.5226. Min Act: -0.1700
Data Index: 1562276 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7730. Min Range: -3.7730
Max Act: 3.5226. Min Act: -0.1700
Data Index: 4919828 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7730. Min Range: -3.7730
Max Act: 3.4757. Min Act: -0.1700
Data Index: 8220493 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7730. Min Range: -3.7730
Max Act: 3.4913. Min Act: -0.1700
Data Index: 2687892 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7730. Min Range: -3.7730
Max Act: 3.4913. Min Act: -0.1700
Data Index: 5575459 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7730. Min Range: -3.7730
Max Act: 3.4443. Min Act: -0.1700
Data Index: 2023287 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7730. Min Range: -3.7730
Max Act: 3.4443. Min Act: -0.1700
Data Index: 4408119 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7730. Min Range: -3.7730
Max Act: 3.4443. Min Act: -0.1700
Data Index: 3681279 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7730. Min Range: -3.7730
Max Act: 3.4443. Min Act: -0.1700
Data Index: 5803099 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7730. Min Range: -3.7730
Max Act: 3.4130. Min Act: -0.1700
Data Index: 6462027 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7730. Min Range: -3.7730
Max Act: 3.4130. Min Act: -0.1700
Data Index: 708697 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7730. Min Range: -3.7730
Max Act: 3.4130. Min Act: -0.1700
Data Index: 1488002 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7730. Min Range: -3.7730
Max Act: 3.4130. Min Act: -0.1700
Data Index: 5606620 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7730. Min Range: -3.7730
Max Act: 3.4130. Min Act: -0.1700
Data Index: 3118647 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7730. Min Range: -3.7730
Max Act: 3.3816. Min Act: -0.1700
Data Index: 1380849 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7730. Min Range: -3.7730
Max Act: 3.3816. Min Act: -0.1700
Data Index: 5564656 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7730. Min Range: -3.7730
Max Act: 3.3659. Min Act: -0.1700
Data Index: 1588589 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7730. Min Range: -3.7730
Max Act: 3.3659. Min Act: -0.1700
Data Index: 1274548 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7730. Min Range: -3.7730
Max Act: 3.3659. Min Act: -0.1700
Data Index: 1281118 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #19