Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 767 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2954. Min Range: -4.2954
Max Act: 4.2954. Min Act: -0.1700
Data Index: 1523788 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2954. Min Range: -4.2954
Max Act: 4.1704. Min Act: -0.1700
Data Index: 7425490 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2954. Min Range: -4.2954
Max Act: 4.0454. Min Act: -0.1700
Data Index: 1526607 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2954. Min Range: -4.2954
Max Act: 4.0141. Min Act: -0.1700
Data Index: 878163 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2954. Min Range: -4.2954
Max Act: 4.0141. Min Act: -0.1700
Data Index: 2618460 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2954. Min Range: -4.2954
Max Act: 3.9828. Min Act: -0.1700
Data Index: 8132683 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2954. Min Range: -4.2954
Max Act: 3.9828. Min Act: -0.1700
Data Index: 8243173 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2954. Min Range: -4.2954
Max Act: 3.9828. Min Act: -0.1700
Data Index: 2770113 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2954. Min Range: -4.2954
Max Act: 3.9516. Min Act: -0.1700
Data Index: 2995300 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2954. Min Range: -4.2954
Max Act: 3.9516. Min Act: -0.1700
Data Index: 400454 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2954. Min Range: -4.2954
Max Act: 3.9203. Min Act: -0.1700
Data Index: 4101900 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2954. Min Range: -4.2954
Max Act: 3.9203. Min Act: -0.1700
Data Index: 2390931 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2954. Min Range: -4.2954
Max Act: 3.9203. Min Act: -0.1700
Data Index: 7238294 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2954. Min Range: -4.2954
Max Act: 3.8890. Min Act: -0.1700
Data Index: 1489939 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2954. Min Range: -4.2954
Max Act: 3.8890. Min Act: -0.1700
Data Index: 1269656 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2954. Min Range: -4.2954
Max Act: 3.8890. Min Act: -0.1700
Data Index: 7066384 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2954. Min Range: -4.2954
Max Act: 3.8890. Min Act: -0.1700
Data Index: 6882443 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2954. Min Range: -4.2954
Max Act: 3.8890. Min Act: -0.1700
Data Index: 255254 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2954. Min Range: -4.2954
Max Act: 3.8890. Min Act: -0.1700
Data Index: 6802847 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2954. Min Range: -4.2954
Max Act: 3.8578. Min Act: -0.1700
Data Index: 6137167 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #19