Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3857 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4875. Min Range: -6.4875
Max Act: 6.4875. Min Act: -0.1700
Data Index: 3569756 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4875. Min Range: -6.4875
Max Act: 6.3625. Min Act: -0.1700
Data Index: 5589803 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4875. Min Range: -6.4875
Max Act: 6.3312. Min Act: -0.1700
Data Index: 729266 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4875. Min Range: -6.4875
Max Act: 6.3312. Min Act: -0.1700
Data Index: 4413439 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4875. Min Range: -6.4875
Max Act: 6.2687. Min Act: -0.1700
Data Index: 7788700 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4875. Min Range: -6.4875
Max Act: 6.3000. Min Act: -0.1700
Data Index: 7328351 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4875. Min Range: -6.4875
Max Act: 6.2687. Min Act: -0.1700
Data Index: 5419378 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4875. Min Range: -6.4875
Max Act: 6.2375. Min Act: -0.1700
Data Index: 7457836 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4875. Min Range: -6.4875
Max Act: 6.2062. Min Act: -0.1700
Data Index: 3479043 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4875. Min Range: -6.4875
Max Act: 6.1750. Min Act: -0.1700
Data Index: 7337007 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4875. Min Range: -6.4875
Max Act: 6.1437. Min Act: -0.1700
Data Index: 940445 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4875. Min Range: -6.4875
Max Act: 6.1437. Min Act: -0.1700
Data Index: 5157917 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4875. Min Range: -6.4875
Max Act: 6.1437. Min Act: -0.1700
Data Index: 1535212 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4875. Min Range: -6.4875
Max Act: 6.1125. Min Act: -0.1700
Data Index: 7910845 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4875. Min Range: -6.4875
Max Act: 6.1125. Min Act: -0.1700
Data Index: 1993175 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4875. Min Range: -6.4875
Max Act: 6.0812. Min Act: -0.1700
Data Index: 7552990 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4875. Min Range: -6.4875
Max Act: 6.0812. Min Act: -0.1700
Data Index: 8640673 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4875. Min Range: -6.4875
Max Act: 6.0500. Min Act: -0.1700
Data Index: 2451136 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4875. Min Range: -6.4875
Max Act: 6.0500. Min Act: -0.1700
Data Index: 8247640 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4875. Min Range: -6.4875
Max Act: 6.0500. Min Act: -0.1700
Data Index: 1752445 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #19