Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 710 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5213. Min Range: -3.5213
Max Act: 3.5213. Min Act: -0.1700
Data Index: 5955764 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5213. Min Range: -3.5213
Max Act: 3.5057. Min Act: -0.1700
Data Index: 5298304 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5213. Min Range: -3.5213
Max Act: 3.4900. Min Act: -0.1700
Data Index: 8290434 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5213. Min Range: -3.5213
Max Act: 3.4116. Min Act: -0.1700
Data Index: 2472002 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5213. Min Range: -3.5213
Max Act: 3.4116. Min Act: -0.1700
Data Index: 3425922 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5213. Min Range: -3.5213
Max Act: 3.4116. Min Act: -0.1700
Data Index: 4684972 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5213. Min Range: -3.5213
Max Act: 3.4116. Min Act: -0.1700
Data Index: 1088841 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5213. Min Range: -3.5213
Max Act: 3.3803. Min Act: -0.1700
Data Index: 5193423 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5213. Min Range: -3.5213
Max Act: 3.3646. Min Act: -0.1700
Data Index: 2409290 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5213. Min Range: -3.5213
Max Act: 3.3332. Min Act: -0.1700
Data Index: 3411001 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5213. Min Range: -3.5213
Max Act: 3.3489. Min Act: -0.1700
Data Index: 8080795 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5213. Min Range: -3.5213
Max Act: 3.3489. Min Act: -0.1700
Data Index: 1959830 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5213. Min Range: -3.5213
Max Act: 3.3332. Min Act: -0.1700
Data Index: 8505686 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5213. Min Range: -3.5213
Max Act: 3.3332. Min Act: -0.1700
Data Index: 23302 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5213. Min Range: -3.5213
Max Act: 3.3175. Min Act: -0.1700
Data Index: 1915696 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5213. Min Range: -3.5213
Max Act: 3.3175. Min Act: -0.1700
Data Index: 7265842 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5213. Min Range: -3.5213
Max Act: 3.2861. Min Act: -0.1700
Data Index: 3645739 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5213. Min Range: -3.5213
Max Act: 3.2704. Min Act: -0.1700
Data Index: 892271 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5213. Min Range: -3.5213
Max Act: 3.2861. Min Act: -0.1700
Data Index: 8155039 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5213. Min Range: -3.5213
Max Act: 3.2390. Min Act: -0.1700
Data Index: 1591876 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #19