Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5455 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.6347. Min Range: -12.6347
Max Act: 12.6347. Min Act: -0.1700
Data Index: 4338497 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.6347. Min Range: -12.6347
Max Act: 12.5722. Min Act: -0.1700
Data Index: 2806173 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.6347. Min Range: -12.6347
Max Act: 12.4472. Min Act: -0.1700
Data Index: 6772403 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.6347. Min Range: -12.6347
Max Act: 12.3222. Min Act: -0.1700
Data Index: 1719236 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.6347. Min Range: -12.6347
Max Act: 12.1972. Min Act: -0.1700
Data Index: 8696641 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.6347. Min Range: -12.6347
Max Act: 12.1347. Min Act: -0.1700
Data Index: 4683414 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.6347. Min Range: -12.6347
Max Act: 12.1347. Min Act: -0.1700
Data Index: 8415653 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.6347. Min Range: -12.6347
Max Act: 12.1347. Min Act: -0.1700
Data Index: 1342580 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.6347. Min Range: -12.6347
Max Act: 12.0097. Min Act: -0.1700
Data Index: 1599660 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.6347. Min Range: -12.6347
Max Act: 12.0097. Min Act: -0.1700
Data Index: 1271584 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.6347. Min Range: -12.6347
Max Act: 12.0097. Min Act: -0.1700
Data Index: 1270467 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.6347. Min Range: -12.6347
Max Act: 12.0722. Min Act: -0.1700
Data Index: 4443028 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.6347. Min Range: -12.6347
Max Act: 12.0097. Min Act: -0.1700
Data Index: 3047359 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.6347. Min Range: -12.6347
Max Act: 12.0097. Min Act: -0.1700
Data Index: 7859938 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.6347. Min Range: -12.6347
Max Act: 11.9472. Min Act: -0.1700
Data Index: 5309675 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.6347. Min Range: -12.6347
Max Act: 11.9472. Min Act: -0.1700
Data Index: 747134 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.6347. Min Range: -12.6347
Max Act: 11.8847. Min Act: -0.1700
Data Index: 1115391 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.6347. Min Range: -12.6347
Max Act: 11.8847. Min Act: -0.1700
Data Index: 601094 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.6347. Min Range: -12.6347
Max Act: 11.8847. Min Act: -0.1700
Data Index: 2817797 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.6347. Min Range: -12.6347
Max Act: 11.8222. Min Act: -0.1700
Data Index: 3308508 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #19