Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4805 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2652. Min Range: -7.2652
Max Act: 7.2652. Min Act: -0.1700
Data Index: 7325550 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2652. Min Range: -7.2652
Max Act: 6.9840. Min Act: -0.1700
Data Index: 1177594 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2652. Min Range: -7.2652
Max Act: 6.9840. Min Act: -0.1700
Data Index: 5282484 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2652. Min Range: -7.2652
Max Act: 6.8902. Min Act: -0.1700
Data Index: 3048166 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2652. Min Range: -7.2652
Max Act: 6.8277. Min Act: -0.1700
Data Index: 7019329 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2652. Min Range: -7.2652
Max Act: 6.8277. Min Act: -0.1700
Data Index: 6899615 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2652. Min Range: -7.2652
Max Act: 6.7965. Min Act: -0.1700
Data Index: 6192565 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2652. Min Range: -7.2652
Max Act: 6.7340. Min Act: -0.1700
Data Index: 6874660 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2652. Min Range: -7.2652
Max Act: 6.7027. Min Act: -0.1700
Data Index: 157296 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2652. Min Range: -7.2652
Max Act: 6.6715. Min Act: -0.1700
Data Index: 122058 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2652. Min Range: -7.2652
Max Act: 6.6402. Min Act: -0.1700
Data Index: 250667 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2652. Min Range: -7.2652
Max Act: 6.6715. Min Act: -0.1700
Data Index: 6692632 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2652. Min Range: -7.2652
Max Act: 6.6402. Min Act: -0.1700
Data Index: 7684070 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2652. Min Range: -7.2652
Max Act: 6.6090. Min Act: -0.1700
Data Index: 8061949 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2652. Min Range: -7.2652
Max Act: 6.6090. Min Act: -0.1700
Data Index: 3240830 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2652. Min Range: -7.2652
Max Act: 6.6090. Min Act: -0.1700
Data Index: 6983040 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2652. Min Range: -7.2652
Max Act: 6.6090. Min Act: -0.1700
Data Index: 6245180 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2652. Min Range: -7.2652
Max Act: 6.5465. Min Act: -0.1700
Data Index: 995250 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2652. Min Range: -7.2652
Max Act: 6.5777. Min Act: -0.1700
Data Index: 6895685 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2652. Min Range: -7.2652
Max Act: 6.5465. Min Act: -0.1700
Data Index: 2947486 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #19