Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4175 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9853. Min Range: -7.9853
Max Act: 7.9853. Min Act: -0.1700
Data Index: 5716315 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9853. Min Range: -7.9853
Max Act: 7.9228. Min Act: -0.1700
Data Index: 5226072 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9853. Min Range: -7.9853
Max Act: 7.9228. Min Act: -0.1700
Data Index: 2905638 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9853. Min Range: -7.9853
Max Act: 7.9228. Min Act: -0.1700
Data Index: 4693091 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9853. Min Range: -7.9853
Max Act: 7.7666. Min Act: -0.1700
Data Index: 2122520 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9853. Min Range: -7.9853
Max Act: 7.7666. Min Act: -0.1700
Data Index: 7776805 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9853. Min Range: -7.9853
Max Act: 7.7666. Min Act: -0.1700
Data Index: 8310963 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9853. Min Range: -7.9853
Max Act: 7.6103. Min Act: -0.1700
Data Index: 3307741 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9853. Min Range: -7.9853
Max Act: 7.6416. Min Act: -0.1700
Data Index: 5406938 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9853. Min Range: -7.9853
Max Act: 7.6416. Min Act: -0.1700
Data Index: 553070 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9853. Min Range: -7.9853
Max Act: 7.6416. Min Act: -0.1700
Data Index: 2183671 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9853. Min Range: -7.9853
Max Act: 7.6103. Min Act: -0.1700
Data Index: 2380118 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9853. Min Range: -7.9853
Max Act: 7.6103. Min Act: -0.1700
Data Index: 519283 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9853. Min Range: -7.9853
Max Act: 7.5791. Min Act: -0.1700
Data Index: 1742873 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9853. Min Range: -7.9853
Max Act: 7.5478. Min Act: -0.1700
Data Index: 718498 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9853. Min Range: -7.9853
Max Act: 7.4853. Min Act: -0.1700
Data Index: 7134971 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9853. Min Range: -7.9853
Max Act: 7.4853. Min Act: -0.1700
Data Index: 3834740 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9853. Min Range: -7.9853
Max Act: 7.4853. Min Act: -0.1700
Data Index: 3873909 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9853. Min Range: -7.9853
Max Act: 7.4541. Min Act: -0.1700
Data Index: 6399639 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9853. Min Range: -7.9853
Max Act: 7.4541. Min Act: -0.1700
Data Index: 2993601 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #19