Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 996 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3078. Min Range: -6.3078
Max Act: 6.3078. Min Act: -0.1700
Data Index: 5568866 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3078. Min Range: -6.3078
Max Act: 5.9641. Min Act: -0.1700
Data Index: 5182714 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3078. Min Range: -6.3078
Max Act: 5.7141. Min Act: -0.1700
Data Index: 8784827 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3078. Min Range: -6.3078
Max Act: 5.7141. Min Act: -0.1700
Data Index: 7361807 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3078. Min Range: -6.3078
Max Act: 5.6828. Min Act: -0.1700
Data Index: 4939406 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3078. Min Range: -6.3078
Max Act: 5.6828. Min Act: -0.1700
Data Index: 647541 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3078. Min Range: -6.3078
Max Act: 5.5891. Min Act: -0.1700
Data Index: 311159 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3078. Min Range: -6.3078
Max Act: 5.5891. Min Act: -0.1700
Data Index: 4581857 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3078. Min Range: -6.3078
Max Act: 5.4953. Min Act: -0.1700
Data Index: 2473128 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3078. Min Range: -6.3078
Max Act: 5.4953. Min Act: -0.1700
Data Index: 975253 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3078. Min Range: -6.3078
Max Act: 5.4953. Min Act: -0.1700
Data Index: 1227597 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3078. Min Range: -6.3078
Max Act: 5.4641. Min Act: -0.1700
Data Index: 885709 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3078. Min Range: -6.3078
Max Act: 5.4641. Min Act: -0.1700
Data Index: 930034 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3078. Min Range: -6.3078
Max Act: 5.4953. Min Act: -0.1700
Data Index: 4023269 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3078. Min Range: -6.3078
Max Act: 5.4641. Min Act: -0.1700
Data Index: 7530319 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3078. Min Range: -6.3078
Max Act: 5.4641. Min Act: -0.1700
Data Index: 5095065 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3078. Min Range: -6.3078
Max Act: 5.4641. Min Act: -0.1700
Data Index: 2004975 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3078. Min Range: -6.3078
Max Act: 5.4641. Min Act: -0.1700
Data Index: 5975341 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3078. Min Range: -6.3078
Max Act: 5.4328. Min Act: -0.1700
Data Index: 6012755 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3078. Min Range: -6.3078
Max Act: 5.4641. Min Act: -0.1700
Data Index: 8472261 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #19