Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3326 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.0807. Min Range: -12.0807
Max Act: 12.0807. Min Act: -0.1700
Data Index: 4518525 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.0807. Min Range: -12.0807
Max Act: 12.0807. Min Act: -0.1696
Data Index: 7665859 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.0807. Min Range: -12.0807
Max Act: 11.6432. Min Act: -0.1700
Data Index: 1915109 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.0807. Min Range: -12.0807
Max Act: 11.6432. Min Act: -0.1700
Data Index: 5871976 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.0807. Min Range: -12.0807
Max Act: 11.4557. Min Act: -0.1700
Data Index: 973602 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.0807. Min Range: -12.0807
Max Act: 11.3932. Min Act: -0.1700
Data Index: 7683920 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.0807. Min Range: -12.0807
Max Act: 11.3932. Min Act: -0.1700
Data Index: 900147 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.0807. Min Range: -12.0807
Max Act: 11.3307. Min Act: -0.1700
Data Index: 3118919 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.0807. Min Range: -12.0807
Max Act: 11.3307. Min Act: -0.1700
Data Index: 5480199 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.0807. Min Range: -12.0807
Max Act: 11.2057. Min Act: -0.1700
Data Index: 3118918 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.0807. Min Range: -12.0807
Max Act: 11.2057. Min Act: -0.1700
Data Index: 2609993 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.0807. Min Range: -12.0807
Max Act: 11.1432. Min Act: -0.1700
Data Index: 8080772 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.0807. Min Range: -12.0807
Max Act: 11.1432. Min Act: -0.1700
Data Index: 6486797 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.0807. Min Range: -12.0807
Max Act: 11.0807. Min Act: -0.1700
Data Index: 6023944 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.0807. Min Range: -12.0807
Max Act: 11.0807. Min Act: -0.1699
Data Index: 6167554 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.0807. Min Range: -12.0807
Max Act: 10.8932. Min Act: -0.1700
Data Index: 3935360 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.0807. Min Range: -12.0807
Max Act: 10.8932. Min Act: -0.1700
Data Index: 478978 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.0807. Min Range: -12.0807
Max Act: 10.8307. Min Act: -0.1700
Data Index: 1959169 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.0807. Min Range: -12.0807
Max Act: 10.8307. Min Act: -0.1700
Data Index: 1915114 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.0807. Min Range: -12.0807
Max Act: 10.7057. Min Act: -0.1700
Data Index: 5480198 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #19