Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2753 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 1.8188. Min Range: -1.8188
Max Act: 1.8188. Min Act: -0.1700
Data Index: 7301331 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8188. Min Range: -1.8188
Max Act: 1.7844. Min Act: -0.1700
Data Index: 6581470 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8188. Min Range: -1.8188
Max Act: 1.7671. Min Act: -0.1700
Data Index: 5282717 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8188. Min Range: -1.8188
Max Act: 1.7585. Min Act: -0.1700
Data Index: 8264935 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8188. Min Range: -1.8188
Max Act: 1.7585. Min Act: -0.1700
Data Index: 796841 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8188. Min Range: -1.8188
Max Act: 1.7499. Min Act: -0.1700
Data Index: 5340792 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8188. Min Range: -1.8188
Max Act: 1.7412. Min Act: -0.1700
Data Index: 437207 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8188. Min Range: -1.8188
Max Act: 1.7326. Min Act: -0.1700
Data Index: 5432129 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8188. Min Range: -1.8188
Max Act: 1.7239. Min Act: -0.1700
Data Index: 3991478 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8188. Min Range: -1.8188
Max Act: 1.7239. Min Act: -0.1700
Data Index: 6438562 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8188. Min Range: -1.8188
Max Act: 1.7239. Min Act: -0.1700
Data Index: 7453205 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8188. Min Range: -1.8188
Max Act: 1.7239. Min Act: -0.1700
Data Index: 2918020 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8188. Min Range: -1.8188
Max Act: 1.7066. Min Act: -0.1700
Data Index: 7818910 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8188. Min Range: -1.8188
Max Act: 1.7153. Min Act: -0.1700
Data Index: 3088527 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8188. Min Range: -1.8188
Max Act: 1.7153. Min Act: -0.1700
Data Index: 1958584 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8188. Min Range: -1.8188
Max Act: 1.7239. Min Act: -0.1700
Data Index: 7000144 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8188. Min Range: -1.8188
Max Act: 1.7066. Min Act: -0.1697
Data Index: 4880230 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8188. Min Range: -1.8188
Max Act: 1.7153. Min Act: -0.1700
Data Index: 1514255 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8188. Min Range: -1.8188
Max Act: 1.7153. Min Act: -0.1700
Data Index: 986547 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8188. Min Range: -1.8188
Max Act: 1.6979. Min Act: -0.1700
Data Index: 700153 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #19