Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2140 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2068. Min Range: -8.2068
Max Act: 8.2068. Min Act: -0.1700
Data Index: 1627184 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2068. Min Range: -8.2068
Max Act: 7.8943. Min Act: -0.1700
Data Index: 7805037 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2068. Min Range: -8.2068
Max Act: 7.8943. Min Act: -0.1700
Data Index: 6589778 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2068. Min Range: -8.2068
Max Act: 7.7693. Min Act: -0.1700
Data Index: 1637138 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2068. Min Range: -8.2068
Max Act: 7.7068. Min Act: -0.1700
Data Index: 7044208 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2068. Min Range: -8.2068
Max Act: 7.7068. Min Act: -0.1700
Data Index: 4387063 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2068. Min Range: -8.2068
Max Act: 7.7068. Min Act: -0.1700
Data Index: 4414963 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2068. Min Range: -8.2068
Max Act: 7.6443. Min Act: -0.1700
Data Index: 1646263 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2068. Min Range: -8.2068
Max Act: 7.6443. Min Act: -0.1700
Data Index: 5240148 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2068. Min Range: -8.2068
Max Act: 7.5818. Min Act: -0.1700
Data Index: 3148788 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2068. Min Range: -8.2068
Max Act: 7.5193. Min Act: -0.1700
Data Index: 7880423 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2068. Min Range: -8.2068
Max Act: 7.4880. Min Act: -0.1700
Data Index: 2834353 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2068. Min Range: -8.2068
Max Act: 7.4255. Min Act: -0.1700
Data Index: 4526371 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2068. Min Range: -8.2068
Max Act: 7.3943. Min Act: -0.1700
Data Index: 116107 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2068. Min Range: -8.2068
Max Act: 7.3943. Min Act: -0.1700
Data Index: 4281406 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2068. Min Range: -8.2068
Max Act: 7.3943. Min Act: -0.1700
Data Index: 8629988 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2068. Min Range: -8.2068
Max Act: 7.4255. Min Act: -0.1700
Data Index: 5996915 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2068. Min Range: -8.2068
Max Act: 7.3630. Min Act: -0.1700
Data Index: 5734846 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2068. Min Range: -8.2068
Max Act: 7.3318. Min Act: -0.1700
Data Index: 7846779 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2068. Min Range: -8.2068
Max Act: 7.3005. Min Act: -0.1700
Data Index: 2888845 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #19