Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1564 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7778. Min Range: -8.7778
Max Act: 8.7778. Min Act: -0.1700
Data Index: 2153918 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7778. Min Range: -8.7778
Max Act: 8.5903. Min Act: -0.1700
Data Index: 2469351 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7778. Min Range: -8.7778
Max Act: 8.4965. Min Act: -0.1700
Data Index: 1196892 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7778. Min Range: -8.7778
Max Act: 8.4965. Min Act: -0.1700
Data Index: 3018058 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7778. Min Range: -8.7778
Max Act: 8.3403. Min Act: -0.1700
Data Index: 4490262 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7778. Min Range: -8.7778
Max Act: 8.3090. Min Act: -0.1700
Data Index: 2139377 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7778. Min Range: -8.7778
Max Act: 8.2778. Min Act: -0.1700
Data Index: 5104902 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7778. Min Range: -8.7778
Max Act: 8.2465. Min Act: -0.1700
Data Index: 1155860 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7778. Min Range: -8.7778
Max Act: 8.2153. Min Act: -0.1700
Data Index: 8016097 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7778. Min Range: -8.7778
Max Act: 8.1215. Min Act: -0.1700
Data Index: 4687399 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7778. Min Range: -8.7778
Max Act: 8.0590. Min Act: -0.1700
Data Index: 3634577 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7778. Min Range: -8.7778
Max Act: 8.1215. Min Act: -0.1700
Data Index: 4029248 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7778. Min Range: -8.7778
Max Act: 8.1215. Min Act: -0.1700
Data Index: 8354359 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7778. Min Range: -8.7778
Max Act: 8.0903. Min Act: -0.1700
Data Index: 7470945 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7778. Min Range: -8.7778
Max Act: 8.0903. Min Act: -0.1700
Data Index: 8305652 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7778. Min Range: -8.7778
Max Act: 8.0590. Min Act: -0.1700
Data Index: 1321085 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7778. Min Range: -8.7778
Max Act: 8.0903. Min Act: -0.1700
Data Index: 3591584 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7778. Min Range: -8.7778
Max Act: 8.0278. Min Act: -0.1700
Data Index: 7754250 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7778. Min Range: -8.7778
Max Act: 8.0278. Min Act: -0.1700
Data Index: 7344512 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7778. Min Range: -8.7778
Max Act: 7.9653. Min Act: -0.1700
Data Index: 300393 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #19