Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5181 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8747. Min Range: -5.8747
Max Act: 5.8747. Min Act: -0.1700
Data Index: 6685635 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8747. Min Range: -5.8747
Max Act: 5.8747. Min Act: -0.1700
Data Index: 5843909 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8747. Min Range: -5.8747
Max Act: 5.8122. Min Act: -0.1700
Data Index: 342619 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8747. Min Range: -5.8747
Max Act: 5.7497. Min Act: -0.1700
Data Index: 2274459 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8747. Min Range: -5.8747
Max Act: 5.7497. Min Act: -0.1700
Data Index: 7054902 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8747. Min Range: -5.8747
Max Act: 5.7497. Min Act: -0.1700
Data Index: 1361586 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8747. Min Range: -5.8747
Max Act: 5.7185. Min Act: -0.1700
Data Index: 2859354 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8747. Min Range: -5.8747
Max Act: 5.7185. Min Act: -0.1700
Data Index: 7341910 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8747. Min Range: -5.8747
Max Act: 5.7185. Min Act: -0.1700
Data Index: 7446148 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8747. Min Range: -5.8747
Max Act: 5.6872. Min Act: -0.1700
Data Index: 8493353 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8747. Min Range: -5.8747
Max Act: 5.6872. Min Act: -0.1700
Data Index: 4972834 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8747. Min Range: -5.8747
Max Act: 5.6872. Min Act: -0.1700
Data Index: 4876040 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8747. Min Range: -5.8747
Max Act: 5.6872. Min Act: -0.1700
Data Index: 3736934 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8747. Min Range: -5.8747
Max Act: 5.6560. Min Act: -0.1700
Data Index: 2120744 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8747. Min Range: -5.8747
Max Act: 5.6247. Min Act: -0.1700
Data Index: 6533246 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8747. Min Range: -5.8747
Max Act: 5.6560. Min Act: -0.1700
Data Index: 5822650 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8747. Min Range: -5.8747
Max Act: 5.6247. Min Act: -0.1700
Data Index: 7909139 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8747. Min Range: -5.8747
Max Act: 5.6247. Min Act: -0.1700
Data Index: 4617485 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8747. Min Range: -5.8747
Max Act: 5.6247. Min Act: -0.1700
Data Index: 1570604 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8747. Min Range: -5.8747
Max Act: 5.6247. Min Act: -0.1700
Data Index: 76933 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #19