Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6276 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.8154. Min Range: -9.8154
Max Act: 9.8154. Min Act: -0.1700
Data Index: 4324579 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.8154. Min Range: -9.8154
Max Act: 9.6279. Min Act: -0.1700
Data Index: 3329813 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.8154. Min Range: -9.8154
Max Act: 9.1904. Min Act: -0.1700
Data Index: 4900104 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.8154. Min Range: -9.8154
Max Act: 9.1279. Min Act: -0.1700
Data Index: 7191656 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.8154. Min Range: -9.8154
Max Act: 8.8779. Min Act: -0.1700
Data Index: 6461635 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.8154. Min Range: -9.8154
Max Act: 8.6904. Min Act: -0.1700
Data Index: 8010780 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.8154. Min Range: -9.8154
Max Act: 8.5654. Min Act: -0.1700
Data Index: 3016742 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.8154. Min Range: -9.8154
Max Act: 8.6904. Min Act: -0.1700
Data Index: 2037273 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.8154. Min Range: -9.8154
Max Act: 8.6279. Min Act: -0.1700
Data Index: 4093057 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.8154. Min Range: -9.8154
Max Act: 8.5654. Min Act: -0.1700
Data Index: 3204770 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.8154. Min Range: -9.8154
Max Act: 8.5654. Min Act: -0.1700
Data Index: 4324581 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.8154. Min Range: -9.8154
Max Act: 8.5654. Min Act: -0.1700
Data Index: 3567461 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.8154. Min Range: -9.8154
Max Act: 8.5654. Min Act: -0.1700
Data Index: 76755 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.8154. Min Range: -9.8154
Max Act: 8.5029. Min Act: -0.1700
Data Index: 1680397 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.8154. Min Range: -9.8154
Max Act: 8.5029. Min Act: -0.1700
Data Index: 20655 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.8154. Min Range: -9.8154
Max Act: 8.5029. Min Act: -0.1700
Data Index: 836588 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.8154. Min Range: -9.8154
Max Act: 8.4404. Min Act: -0.1700
Data Index: 8019129 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.8154. Min Range: -9.8154
Max Act: 8.4404. Min Act: -0.1700
Data Index: 2471995 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.8154. Min Range: -9.8154
Max Act: 8.4404. Min Act: -0.1700
Data Index: 4966697 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.8154. Min Range: -9.8154
Max Act: 8.3779. Min Act: -0.1700
Data Index: 2827286 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #19