Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2973 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3150. Min Range: -5.3150
Max Act: 5.3150. Min Act: -0.1700
Data Index: 5895855 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3150. Min Range: -5.3150
Max Act: 5.1275. Min Act: -0.1700
Data Index: 8216521 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3150. Min Range: -5.3150
Max Act: 5.0963. Min Act: -0.1700
Data Index: 1592866 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3150. Min Range: -5.3150
Max Act: 5.0963. Min Act: -0.1700
Data Index: 5974325 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3150. Min Range: -5.3150
Max Act: 5.0650. Min Act: -0.1700
Data Index: 7476282 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3150. Min Range: -5.3150
Max Act: 5.0025. Min Act: -0.1700
Data Index: 7476285 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3150. Min Range: -5.3150
Max Act: 5.0025. Min Act: -0.1700
Data Index: 7476279 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3150. Min Range: -5.3150
Max Act: 4.9088. Min Act: -0.1700
Data Index: 5584059 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3150. Min Range: -5.3150
Max Act: 4.9088. Min Act: -0.1700
Data Index: 4969392 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3150. Min Range: -5.3150
Max Act: 4.7838. Min Act: -0.1700
Data Index: 5643187 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3150. Min Range: -5.3150
Max Act: 4.7838. Min Act: -0.1700
Data Index: 7466699 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3150. Min Range: -5.3150
Max Act: 4.8150. Min Act: -0.1700
Data Index: 7930325 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3150. Min Range: -5.3150
Max Act: 4.7525. Min Act: -0.1700
Data Index: 5299205 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3150. Min Range: -5.3150
Max Act: 4.7525. Min Act: -0.1700
Data Index: 5502041 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3150. Min Range: -5.3150
Max Act: 4.7525. Min Act: -0.1700
Data Index: 5234510 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3150. Min Range: -5.3150
Max Act: 4.7213. Min Act: -0.1700
Data Index: 3613328 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3150. Min Range: -5.3150
Max Act: 4.6900. Min Act: -0.1700
Data Index: 4528103 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3150. Min Range: -5.3150
Max Act: 4.6588. Min Act: -0.1700
Data Index: 1166030 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3150. Min Range: -5.3150
Max Act: 4.6588. Min Act: -0.1700
Data Index: 3685740 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3150. Min Range: -5.3150
Max Act: 4.6588. Min Act: -0.1700
Data Index: 4039405 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #19