Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2719 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2990. Min Range: -7.2990
Max Act: 7.2990. Min Act: -0.1700
Data Index: 1608216 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2990. Min Range: -7.2990
Max Act: 7.1428. Min Act: -0.1700
Data Index: 7430221 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2990. Min Range: -7.2990
Max Act: 7.1428. Min Act: -0.1700
Data Index: 5395291 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2990. Min Range: -7.2990
Max Act: 7.1115. Min Act: -0.1700
Data Index: 1828642 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2990. Min Range: -7.2990
Max Act: 6.9553. Min Act: -0.1700
Data Index: 6065376 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2990. Min Range: -7.2990
Max Act: 6.8615. Min Act: -0.1700
Data Index: 8588669 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2990. Min Range: -7.2990
Max Act: 6.8303. Min Act: -0.1700
Data Index: 3409849 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2990. Min Range: -7.2990
Max Act: 6.7990. Min Act: -0.1700
Data Index: 3302808 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2990. Min Range: -7.2990
Max Act: 6.7990. Min Act: -0.1700
Data Index: 8269052 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2990. Min Range: -7.2990
Max Act: 6.7990. Min Act: -0.1700
Data Index: 1341476 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2990. Min Range: -7.2990
Max Act: 6.7990. Min Act: -0.1700
Data Index: 7561945 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2990. Min Range: -7.2990
Max Act: 6.7678. Min Act: -0.1700
Data Index: 8558292 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2990. Min Range: -7.2990
Max Act: 6.6740. Min Act: -0.1700
Data Index: 5617640 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2990. Min Range: -7.2990
Max Act: 6.7053. Min Act: -0.1700
Data Index: 7653136 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2990. Min Range: -7.2990
Max Act: 6.6740. Min Act: -0.1700
Data Index: 8191993 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2990. Min Range: -7.2990
Max Act: 6.6740. Min Act: -0.1700
Data Index: 5821000 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2990. Min Range: -7.2990
Max Act: 6.6115. Min Act: -0.1700
Data Index: 8455117 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2990. Min Range: -7.2990
Max Act: 6.6428. Min Act: -0.1700
Data Index: 5472427 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2990. Min Range: -7.2990
Max Act: 6.6428. Min Act: -0.1700
Data Index: 1493281 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2990. Min Range: -7.2990
Max Act: 6.6428. Min Act: -0.1700
Data Index: 1949132 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #19