Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6098 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3094. Min Range: -6.3094
Max Act: 6.3094. Min Act: -0.1700
Data Index: 960998 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3094. Min Range: -6.3094
Max Act: 6.2781. Min Act: -0.1700
Data Index: 4304877 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3094. Min Range: -6.3094
Max Act: 6.1219. Min Act: -0.1700
Data Index: 3553517 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3094. Min Range: -6.3094
Max Act: 6.0906. Min Act: -0.1700
Data Index: 8037466 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3094. Min Range: -6.3094
Max Act: 5.9656. Min Act: -0.1700
Data Index: 7902224 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3094. Min Range: -6.3094
Max Act: 5.9969. Min Act: -0.1700
Data Index: 4543144 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3094. Min Range: -6.3094
Max Act: 5.9344. Min Act: -0.1700
Data Index: 2441226 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3094. Min Range: -6.3094
Max Act: 5.9344. Min Act: -0.1700
Data Index: 559413 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3094. Min Range: -6.3094
Max Act: 5.9344. Min Act: -0.1700
Data Index: 7104409 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3094. Min Range: -6.3094
Max Act: 5.9656. Min Act: -0.1700
Data Index: 1920044 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3094. Min Range: -6.3094
Max Act: 5.8719. Min Act: -0.1700
Data Index: 1904474 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3094. Min Range: -6.3094
Max Act: 5.8719. Min Act: -0.1700
Data Index: 7826339 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3094. Min Range: -6.3094
Max Act: 5.8094. Min Act: -0.1700
Data Index: 619544 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3094. Min Range: -6.3094
Max Act: 5.8094. Min Act: -0.1700
Data Index: 416593 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3094. Min Range: -6.3094
Max Act: 5.8094. Min Act: -0.1700
Data Index: 8629458 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3094. Min Range: -6.3094
Max Act: 5.8406. Min Act: -0.1700
Data Index: 278928 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3094. Min Range: -6.3094
Max Act: 5.8094. Min Act: -0.1700
Data Index: 8020703 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3094. Min Range: -6.3094
Max Act: 5.7469. Min Act: -0.1700
Data Index: 558583 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3094. Min Range: -6.3094
Max Act: 5.7781. Min Act: -0.1700
Data Index: 1760011 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3094. Min Range: -6.3094
Max Act: 5.7781. Min Act: -0.1700
Data Index: 299722 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #19