Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3134 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4730. Min Range: -6.4730
Max Act: 6.4730. Min Act: -0.1700
Data Index: 7213184 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4730. Min Range: -6.4730
Max Act: 6.4730. Min Act: -0.1700
Data Index: 3058956 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4730. Min Range: -6.4730
Max Act: 6.4105. Min Act: -0.1700
Data Index: 7521706 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4730. Min Range: -6.4730
Max Act: 6.3793. Min Act: -0.1700
Data Index: 813879 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4730. Min Range: -6.4730
Max Act: 6.2855. Min Act: -0.1700
Data Index: 7335364 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4730. Min Range: -6.4730
Max Act: 6.2855. Min Act: -0.1700
Data Index: 3081284 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4730. Min Range: -6.4730
Max Act: 6.2543. Min Act: -0.1700
Data Index: 4947171 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4730. Min Range: -6.4730
Max Act: 6.2543. Min Act: -0.1700
Data Index: 6400795 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4730. Min Range: -6.4730
Max Act: 6.2543. Min Act: -0.1700
Data Index: 6680907 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4730. Min Range: -6.4730
Max Act: 6.2230. Min Act: -0.1700
Data Index: 3469678 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4730. Min Range: -6.4730
Max Act: 6.2230. Min Act: -0.1700
Data Index: 1613697 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4730. Min Range: -6.4730
Max Act: 6.2230. Min Act: -0.1700
Data Index: 1185661 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4730. Min Range: -6.4730
Max Act: 6.2230. Min Act: -0.1700
Data Index: 1676088 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4730. Min Range: -6.4730
Max Act: 6.2230. Min Act: -0.1700
Data Index: 5754562 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4730. Min Range: -6.4730
Max Act: 6.2543. Min Act: -0.1700
Data Index: 7572628 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4730. Min Range: -6.4730
Max Act: 6.2543. Min Act: -0.1700
Data Index: 5587774 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4730. Min Range: -6.4730
Max Act: 6.2230. Min Act: -0.1700
Data Index: 502199 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4730. Min Range: -6.4730
Max Act: 6.1918. Min Act: -0.1700
Data Index: 5694907 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4730. Min Range: -6.4730
Max Act: 6.1918. Min Act: -0.1700
Data Index: 2644272 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4730. Min Range: -6.4730
Max Act: 6.1918. Min Act: -0.1700
Data Index: 1578117 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #19