Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4221 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7300. Min Range: -8.7300
Max Act: 8.7300. Min Act: -0.1700
Data Index: 6571038 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7300. Min Range: -8.7300
Max Act: 8.6050. Min Act: -0.1700
Data Index: 8605194 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7300. Min Range: -8.7300
Max Act: 8.6050. Min Act: -0.1700
Data Index: 4390604 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7300. Min Range: -8.7300
Max Act: 8.6050. Min Act: -0.1700
Data Index: 6232874 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7300. Min Range: -8.7300
Max Act: 8.4800. Min Act: -0.1700
Data Index: 5657220 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7300. Min Range: -8.7300
Max Act: 8.4175. Min Act: -0.1700
Data Index: 4859307 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7300. Min Range: -8.7300
Max Act: 8.4175. Min Act: -0.1700
Data Index: 1535564 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7300. Min Range: -8.7300
Max Act: 8.3550. Min Act: -0.1700
Data Index: 5773475 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7300. Min Range: -8.7300
Max Act: 8.3550. Min Act: -0.1700
Data Index: 3842002 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7300. Min Range: -8.7300
Max Act: 8.2925. Min Act: -0.1700
Data Index: 2830876 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7300. Min Range: -8.7300
Max Act: 8.2925. Min Act: -0.1700
Data Index: 4859308 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7300. Min Range: -8.7300
Max Act: 8.2925. Min Act: -0.1700
Data Index: 7999914 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7300. Min Range: -8.7300
Max Act: 8.2300. Min Act: -0.1700
Data Index: 3421884 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7300. Min Range: -8.7300
Max Act: 8.2300. Min Act: -0.1700
Data Index: 7689895 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7300. Min Range: -8.7300
Max Act: 8.2300. Min Act: -0.1700
Data Index: 687898 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7300. Min Range: -8.7300
Max Act: 8.2300. Min Act: -0.1700
Data Index: 403228 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7300. Min Range: -8.7300
Max Act: 8.2300. Min Act: -0.1700
Data Index: 4959751 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7300. Min Range: -8.7300
Max Act: 8.1675. Min Act: -0.1700
Data Index: 452632 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7300. Min Range: -8.7300
Max Act: 8.1675. Min Act: -0.1700
Data Index: 6860212 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7300. Min Range: -8.7300
Max Act: 8.1675. Min Act: -0.1700
Data Index: 4435310 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #19