Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4906 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4276. Min Range: -5.4276
Max Act: 5.4276. Min Act: -0.1700
Data Index: 6859795 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4276. Min Range: -5.4276
Max Act: 5.3339. Min Act: -0.1700
Data Index: 2948199 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4276. Min Range: -5.4276
Max Act: 5.3339. Min Act: -0.1700
Data Index: 1568387 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4276. Min Range: -5.4276
Max Act: 5.3026. Min Act: -0.1700
Data Index: 4770650 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4276. Min Range: -5.4276
Max Act: 5.2401. Min Act: -0.1700
Data Index: 35428 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4276. Min Range: -5.4276
Max Act: 5.2401. Min Act: -0.1700
Data Index: 6975963 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4276. Min Range: -5.4276
Max Act: 5.1776. Min Act: -0.1700
Data Index: 2713540 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4276. Min Range: -5.4276
Max Act: 5.1776. Min Act: -0.1700
Data Index: 4680201 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4276. Min Range: -5.4276
Max Act: 5.1776. Min Act: -0.1700
Data Index: 3647988 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4276. Min Range: -5.4276
Max Act: 5.1464. Min Act: -0.1700
Data Index: 5806197 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4276. Min Range: -5.4276
Max Act: 5.1464. Min Act: -0.1700
Data Index: 6959396 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4276. Min Range: -5.4276
Max Act: 5.1151. Min Act: -0.1700
Data Index: 8565783 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4276. Min Range: -5.4276
Max Act: 5.0839. Min Act: -0.1700
Data Index: 6677827 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4276. Min Range: -5.4276
Max Act: 5.1151. Min Act: -0.1700
Data Index: 3935139 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4276. Min Range: -5.4276
Max Act: 5.0839. Min Act: -0.1700
Data Index: 519334 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4276. Min Range: -5.4276
Max Act: 5.1151. Min Act: -0.1700
Data Index: 7935993 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4276. Min Range: -5.4276
Max Act: 5.1151. Min Act: -0.1700
Data Index: 5003916 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4276. Min Range: -5.4276
Max Act: 5.1464. Min Act: -0.1700
Data Index: 1664568 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4276. Min Range: -5.4276
Max Act: 5.0839. Min Act: -0.1700
Data Index: 6669695 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4276. Min Range: -5.4276
Max Act: 5.0839. Min Act: -0.1700
Data Index: 7235901 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #19