Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 709 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.7595. Min Range: -9.7595
Max Act: 9.7595. Min Act: -0.1700
Data Index: 5813351 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.7595. Min Range: -9.7595
Max Act: 9.7595. Min Act: -0.1700
Data Index: 4000598 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.7595. Min Range: -9.7595
Max Act: 9.7595. Min Act: -0.1700
Data Index: 868461 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.7595. Min Range: -9.7595
Max Act: 9.7595. Min Act: -0.1700
Data Index: 5918496 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.7595. Min Range: -9.7595
Max Act: 9.6970. Min Act: -0.1700
Data Index: 2791537 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.7595. Min Range: -9.7595
Max Act: 9.6970. Min Act: -0.1700
Data Index: 3417786 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.7595. Min Range: -9.7595
Max Act: 9.6970. Min Act: -0.1700
Data Index: 4013741 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.7595. Min Range: -9.7595
Max Act: 9.6345. Min Act: -0.1700
Data Index: 3101445 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.7595. Min Range: -9.7595
Max Act: 9.5720. Min Act: -0.1700
Data Index: 1506530 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.7595. Min Range: -9.7595
Max Act: 9.5095. Min Act: -0.1700
Data Index: 3378693 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.7595. Min Range: -9.7595
Max Act: 9.5095. Min Act: -0.1700
Data Index: 4548161 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.7595. Min Range: -9.7595
Max Act: 9.4470. Min Act: -0.1700
Data Index: 8400379 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.7595. Min Range: -9.7595
Max Act: 9.3845. Min Act: -0.1700
Data Index: 4356210 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.7595. Min Range: -9.7595
Max Act: 9.3845. Min Act: -0.1700
Data Index: 1028247 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.7595. Min Range: -9.7595
Max Act: 9.3845. Min Act: -0.1700
Data Index: 8440522 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.7595. Min Range: -9.7595
Max Act: 9.3845. Min Act: -0.1700
Data Index: 5701608 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.7595. Min Range: -9.7595
Max Act: 9.3845. Min Act: -0.1700
Data Index: 3128632 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.7595. Min Range: -9.7595
Max Act: 9.3220. Min Act: -0.1700
Data Index: 4881446 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.7595. Min Range: -9.7595
Max Act: 9.3220. Min Act: -0.1700
Data Index: 1410743 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.7595. Min Range: -9.7595
Max Act: 9.3220. Min Act: -0.1700
Data Index: 3685955 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #19