Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5194 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0055. Min Range: -6.0055
Max Act: 6.0055. Min Act: -0.1700
Data Index: 3012251 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0055. Min Range: -6.0055
Max Act: 5.9117. Min Act: -0.1700
Data Index: 7859068 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0055. Min Range: -6.0055
Max Act: 5.8492. Min Act: -0.1700
Data Index: 5111443 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0055. Min Range: -6.0055
Max Act: 5.8492. Min Act: -0.1700
Data Index: 3562258 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0055. Min Range: -6.0055
Max Act: 5.8492. Min Act: -0.1700
Data Index: 7322712 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0055. Min Range: -6.0055
Max Act: 5.8492. Min Act: -0.1700
Data Index: 8733938 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0055. Min Range: -6.0055
Max Act: 5.7867. Min Act: -0.1700
Data Index: 2922737 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0055. Min Range: -6.0055
Max Act: 5.7555. Min Act: -0.1700
Data Index: 4313980 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0055. Min Range: -6.0055
Max Act: 5.7555. Min Act: -0.1700
Data Index: 6851635 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0055. Min Range: -6.0055
Max Act: 5.7242. Min Act: -0.1700
Data Index: 1768025 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0055. Min Range: -6.0055
Max Act: 5.7242. Min Act: -0.1700
Data Index: 1523149 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0055. Min Range: -6.0055
Max Act: 5.7555. Min Act: -0.1700
Data Index: 1548557 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0055. Min Range: -6.0055
Max Act: 5.6930. Min Act: -0.1700
Data Index: 3802567 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0055. Min Range: -6.0055
Max Act: 5.6930. Min Act: -0.1700
Data Index: 7908283 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0055. Min Range: -6.0055
Max Act: 5.6617. Min Act: -0.1700
Data Index: 8406101 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0055. Min Range: -6.0055
Max Act: 5.6617. Min Act: -0.1700
Data Index: 253344 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0055. Min Range: -6.0055
Max Act: 5.6305. Min Act: -0.1700
Data Index: 3108538 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0055. Min Range: -6.0055
Max Act: 5.6305. Min Act: -0.1700
Data Index: 5241757 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0055. Min Range: -6.0055
Max Act: 5.6305. Min Act: -0.1700
Data Index: 2100621 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0055. Min Range: -6.0055
Max Act: 5.6305. Min Act: -0.1700
Data Index: 7866464 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #19