Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 278 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8551. Min Range: -6.8551
Max Act: 6.8551. Min Act: -0.1700
Data Index: 3194631 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8551. Min Range: -6.8551
Max Act: 6.6989. Min Act: -0.1700
Data Index: 6943736 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8551. Min Range: -6.8551
Max Act: 6.6676. Min Act: -0.1700
Data Index: 882024 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8551. Min Range: -6.8551
Max Act: 6.6676. Min Act: -0.1700
Data Index: 5695025 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8551. Min Range: -6.8551
Max Act: 6.6676. Min Act: -0.1700
Data Index: 1553832 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8551. Min Range: -6.8551
Max Act: 6.6364. Min Act: -0.1700
Data Index: 7693114 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8551. Min Range: -6.8551
Max Act: 6.6051. Min Act: -0.1700
Data Index: 3455268 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8551. Min Range: -6.8551
Max Act: 6.5114. Min Act: -0.1700
Data Index: 1407328 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8551. Min Range: -6.8551
Max Act: 6.4489. Min Act: -0.1700
Data Index: 6209689 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8551. Min Range: -6.8551
Max Act: 6.3864. Min Act: -0.1700
Data Index: 8666687 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8551. Min Range: -6.8551
Max Act: 6.4176. Min Act: -0.1700
Data Index: 6470686 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8551. Min Range: -6.8551
Max Act: 6.3864. Min Act: -0.1700
Data Index: 1690907 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8551. Min Range: -6.8551
Max Act: 6.3864. Min Act: -0.1700
Data Index: 23231 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8551. Min Range: -6.8551
Max Act: 6.3864. Min Act: -0.1700
Data Index: 5897629 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8551. Min Range: -6.8551
Max Act: 6.3551. Min Act: -0.1700
Data Index: 8411587 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8551. Min Range: -6.8551
Max Act: 6.3551. Min Act: -0.1700
Data Index: 6359003 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8551. Min Range: -6.8551
Max Act: 6.3239. Min Act: -0.1700
Data Index: 2723391 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8551. Min Range: -6.8551
Max Act: 6.3239. Min Act: -0.1700
Data Index: 5599427 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8551. Min Range: -6.8551
Max Act: 6.3239. Min Act: -0.1700
Data Index: 4769168 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8551. Min Range: -6.8551
Max Act: 6.3239. Min Act: -0.1700
Data Index: 6843207 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #19