Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3474 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6904. Min Range: -5.6904
Max Act: 5.6904. Min Act: -0.1700
Data Index: 3203720 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6904. Min Range: -5.6904
Max Act: 5.4092. Min Act: -0.1700
Data Index: 2858959 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6904. Min Range: -5.6904
Max Act: 5.4092. Min Act: -0.1700
Data Index: 8719414 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6904. Min Range: -5.6904
Max Act: 5.3779. Min Act: -0.1700
Data Index: 5375623 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6904. Min Range: -5.6904
Max Act: 5.3779. Min Act: -0.1700
Data Index: 5433084 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6904. Min Range: -5.6904
Max Act: 5.3154. Min Act: -0.1700
Data Index: 4819277 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6904. Min Range: -5.6904
Max Act: 5.3154. Min Act: -0.1700
Data Index: 1751791 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6904. Min Range: -5.6904
Max Act: 5.2842. Min Act: -0.1700
Data Index: 8156280 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6904. Min Range: -5.6904
Max Act: 5.2842. Min Act: -0.1700
Data Index: 6468844 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6904. Min Range: -5.6904
Max Act: 5.2842. Min Act: -0.1700
Data Index: 5722857 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6904. Min Range: -5.6904
Max Act: 5.2217. Min Act: -0.1700
Data Index: 2895376 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6904. Min Range: -5.6904
Max Act: 5.1904. Min Act: -0.1700
Data Index: 7356763 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6904. Min Range: -5.6904
Max Act: 5.1592. Min Act: -0.1700
Data Index: 796577 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6904. Min Range: -5.6904
Max Act: 5.1592. Min Act: -0.1700
Data Index: 5025082 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6904. Min Range: -5.6904
Max Act: 5.1592. Min Act: -0.1700
Data Index: 1833600 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6904. Min Range: -5.6904
Max Act: 5.1592. Min Act: -0.1700
Data Index: 6603424 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6904. Min Range: -5.6904
Max Act: 5.1279. Min Act: -0.1700
Data Index: 3656557 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6904. Min Range: -5.6904
Max Act: 5.1592. Min Act: -0.1700
Data Index: 3509068 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6904. Min Range: -5.6904
Max Act: 5.1904. Min Act: -0.1700
Data Index: 7366130 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6904. Min Range: -5.6904
Max Act: 5.1279. Min Act: -0.1700
Data Index: 1574663 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #19