Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3556 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3057. Min Range: -7.3057
Max Act: 7.3057. Min Act: -0.1700
Data Index: 6955386 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3057. Min Range: -7.3057
Max Act: 7.2432. Min Act: -0.1700
Data Index: 7199960 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3057. Min Range: -7.3057
Max Act: 7.2432. Min Act: -0.1700
Data Index: 6619097 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3057. Min Range: -7.3057
Max Act: 7.2432. Min Act: -0.1700
Data Index: 7838017 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3057. Min Range: -7.3057
Max Act: 7.1182. Min Act: -0.1700
Data Index: 8218332 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3057. Min Range: -7.3057
Max Act: 7.0870. Min Act: -0.1700
Data Index: 442310 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3057. Min Range: -7.3057
Max Act: 7.0557. Min Act: -0.1700
Data Index: 4635301 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3057. Min Range: -7.3057
Max Act: 6.9932. Min Act: -0.1700
Data Index: 7294929 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3057. Min Range: -7.3057
Max Act: 6.9307. Min Act: -0.1700
Data Index: 6911339 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3057. Min Range: -7.3057
Max Act: 6.8995. Min Act: -0.1700
Data Index: 2837271 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3057. Min Range: -7.3057
Max Act: 6.8995. Min Act: -0.1700
Data Index: 8680855 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3057. Min Range: -7.3057
Max Act: 6.8995. Min Act: -0.1700
Data Index: 3887135 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3057. Min Range: -7.3057
Max Act: 6.8682. Min Act: -0.1700
Data Index: 2769033 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3057. Min Range: -7.3057
Max Act: 6.8370. Min Act: -0.1700
Data Index: 6009884 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3057. Min Range: -7.3057
Max Act: 6.8370. Min Act: -0.1700
Data Index: 1775583 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3057. Min Range: -7.3057
Max Act: 6.8370. Min Act: -0.1700
Data Index: 5504989 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3057. Min Range: -7.3057
Max Act: 6.8057. Min Act: -0.1700
Data Index: 7572337 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3057. Min Range: -7.3057
Max Act: 6.7745. Min Act: -0.1700
Data Index: 6959181 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3057. Min Range: -7.3057
Max Act: 6.7745. Min Act: -0.1700
Data Index: 3093324 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3057. Min Range: -7.3057
Max Act: 6.7745. Min Act: -0.1700
Data Index: 4431272 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #19