Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4318 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4070. Min Range: -8.4070
Max Act: 8.4070. Min Act: -0.1700
Data Index: 3877360 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4070. Min Range: -8.4070
Max Act: 8.2195. Min Act: -0.1700
Data Index: 1434635 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4070. Min Range: -8.4070
Max Act: 7.7820. Min Act: -0.1700
Data Index: 8480307 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4070. Min Range: -8.4070
Max Act: 7.7820. Min Act: -0.1700
Data Index: 7712596 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4070. Min Range: -8.4070
Max Act: 7.7195. Min Act: -0.1700
Data Index: 6335640 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4070. Min Range: -8.4070
Max Act: 7.7195. Min Act: -0.1700
Data Index: 3848876 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4070. Min Range: -8.4070
Max Act: 7.6570. Min Act: -0.1700
Data Index: 5802948 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4070. Min Range: -8.4070
Max Act: 7.5945. Min Act: -0.1700
Data Index: 8634098 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4070. Min Range: -8.4070
Max Act: 7.5320. Min Act: -0.1700
Data Index: 3359779 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4070. Min Range: -8.4070
Max Act: 7.5008. Min Act: -0.1700
Data Index: 3601277 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4070. Min Range: -8.4070
Max Act: 7.4383. Min Act: -0.1700
Data Index: 7650086 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4070. Min Range: -8.4070
Max Act: 7.4070. Min Act: -0.1700
Data Index: 6114891 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4070. Min Range: -8.4070
Max Act: 7.4383. Min Act: -0.1700
Data Index: 8493622 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4070. Min Range: -8.4070
Max Act: 7.4070. Min Act: -0.1700
Data Index: 315724 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4070. Min Range: -8.4070
Max Act: 7.4383. Min Act: -0.1700
Data Index: 3378629 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4070. Min Range: -8.4070
Max Act: 7.4383. Min Act: -0.1700
Data Index: 6997160 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4070. Min Range: -8.4070
Max Act: 7.3758. Min Act: -0.1700
Data Index: 8824524 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4070. Min Range: -8.4070
Max Act: 7.3758. Min Act: -0.1700
Data Index: 7898114 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4070. Min Range: -8.4070
Max Act: 7.3758. Min Act: -0.1700
Data Index: 2941823 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4070. Min Range: -8.4070
Max Act: 7.3758. Min Act: -0.1700
Data Index: 4785787 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #19