Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3643 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.7363. Min Range: -5.7363
Max Act: 5.7363. Min Act: -0.1700
Data Index: 8380788 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7363. Min Range: -5.7363
Max Act: 5.7363. Min Act: -0.1700
Data Index: 4098149 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7363. Min Range: -5.7363
Max Act: 5.6738. Min Act: -0.1700
Data Index: 58030 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7363. Min Range: -5.7363
Max Act: 5.6426. Min Act: -0.1700
Data Index: 4668923 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7363. Min Range: -5.7363
Max Act: 5.6426. Min Act: -0.1700
Data Index: 1215207 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7363. Min Range: -5.7363
Max Act: 5.6426. Min Act: -0.1700
Data Index: 6494825 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7363. Min Range: -5.7363
Max Act: 5.6113. Min Act: -0.1700
Data Index: 4668922 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7363. Min Range: -5.7363
Max Act: 5.6113. Min Act: -0.1698
Data Index: 2098694 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7363. Min Range: -5.7363
Max Act: 5.5801. Min Act: -0.1700
Data Index: 2020657 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7363. Min Range: -5.7363
Max Act: 5.5801. Min Act: -0.1700
Data Index: 4668927 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7363. Min Range: -5.7363
Max Act: 5.5488. Min Act: -0.1700
Data Index: 2754199 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7363. Min Range: -5.7363
Max Act: 5.5488. Min Act: -0.1700
Data Index: 6768047 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7363. Min Range: -5.7363
Max Act: 5.5488. Min Act: -0.1700
Data Index: 1998392 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7363. Min Range: -5.7363
Max Act: 5.5488. Min Act: -0.1700
Data Index: 1020606 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7363. Min Range: -5.7363
Max Act: 5.5488. Min Act: -0.1700
Data Index: 7131770 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7363. Min Range: -5.7363
Max Act: 5.5176. Min Act: -0.1700
Data Index: 2393756 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7363. Min Range: -5.7363
Max Act: 5.5488. Min Act: -0.1700
Data Index: 4668925 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7363. Min Range: -5.7363
Max Act: 5.5176. Min Act: -0.1700
Data Index: 2098696 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7363. Min Range: -5.7363
Max Act: 5.5488. Min Act: -0.1700
Data Index: 2908910 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7363. Min Range: -5.7363
Max Act: 5.5488. Min Act: -0.1697
Data Index: 2098695 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #19