Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1682 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.0266. Min Range: -10.0266
Max Act: 10.0266. Min Act: -0.1700
Data Index: 42438 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.0266. Min Range: -10.0266
Max Act: 9.9641. Min Act: -0.1700
Data Index: 6665545 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.0266. Min Range: -10.0266
Max Act: 9.9641. Min Act: -0.1700
Data Index: 6713896 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.0266. Min Range: -10.0266
Max Act: 9.9016. Min Act: -0.1700
Data Index: 3206340 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.0266. Min Range: -10.0266
Max Act: 9.9016. Min Act: -0.1700
Data Index: 3959718 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.0266. Min Range: -10.0266
Max Act: 9.8391. Min Act: -0.1700
Data Index: 8692986 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.0266. Min Range: -10.0266
Max Act: 9.7766. Min Act: -0.1700
Data Index: 3199507 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.0266. Min Range: -10.0266
Max Act: 9.5891. Min Act: -0.1700
Data Index: 3653237 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.0266. Min Range: -10.0266
Max Act: 9.6516. Min Act: -0.1700
Data Index: 2535202 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.0266. Min Range: -10.0266
Max Act: 9.5891. Min Act: -0.1700
Data Index: 2245016 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.0266. Min Range: -10.0266
Max Act: 9.6516. Min Act: -0.1700
Data Index: 1051208 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.0266. Min Range: -10.0266
Max Act: 9.6516. Min Act: -0.1700
Data Index: 7995217 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.0266. Min Range: -10.0266
Max Act: 9.6516. Min Act: -0.1700
Data Index: 1903516 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.0266. Min Range: -10.0266
Max Act: 9.4641. Min Act: -0.1700
Data Index: 7311889 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.0266. Min Range: -10.0266
Max Act: 9.4016. Min Act: -0.1700
Data Index: 6847888 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.0266. Min Range: -10.0266
Max Act: 9.2766. Min Act: -0.1700
Data Index: 8208355 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.0266. Min Range: -10.0266
Max Act: 9.2766. Min Act: -0.1700
Data Index: 5881570 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.0266. Min Range: -10.0266
Max Act: 9.2141. Min Act: -0.1700
Data Index: 6900891 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.0266. Min Range: -10.0266
Max Act: 9.1516. Min Act: -0.1700
Data Index: 877639 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.0266. Min Range: -10.0266
Max Act: 9.2141. Min Act: -0.1700
Data Index: 600707 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #19