Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5185 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.2750. Min Range: -11.2750
Max Act: 11.2750. Min Act: -0.1700
Data Index: 7774854 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.2750. Min Range: -11.2750
Max Act: 11.2750. Min Act: -0.1700
Data Index: 7831538 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.2750. Min Range: -11.2750
Max Act: 11.0875. Min Act: -0.1700
Data Index: 2474153 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.2750. Min Range: -11.2750
Max Act: 11.0250. Min Act: -0.1700
Data Index: 7041344 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.2750. Min Range: -11.2750
Max Act: 11.0250. Min Act: -0.1700
Data Index: 6709526 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.2750. Min Range: -11.2750
Max Act: 11.0250. Min Act: -0.1700
Data Index: 5093937 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.2750. Min Range: -11.2750
Max Act: 11.0250. Min Act: -0.1700
Data Index: 1209326 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.2750. Min Range: -11.2750
Max Act: 10.9625. Min Act: -0.1700
Data Index: 75231 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.2750. Min Range: -11.2750
Max Act: 10.9625. Min Act: -0.1700
Data Index: 5277603 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.2750. Min Range: -11.2750
Max Act: 10.9625. Min Act: -0.1700
Data Index: 4701324 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.2750. Min Range: -11.2750
Max Act: 10.9625. Min Act: -0.1700
Data Index: 1315293 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.2750. Min Range: -11.2750
Max Act: 10.9000. Min Act: -0.1700
Data Index: 8505317 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.2750. Min Range: -11.2750
Max Act: 10.9000. Min Act: -0.1700
Data Index: 3067125 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.2750. Min Range: -11.2750
Max Act: 10.9000. Min Act: -0.1700
Data Index: 5469381 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.2750. Min Range: -11.2750
Max Act: 10.9625. Min Act: -0.1700
Data Index: 3644460 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.2750. Min Range: -11.2750
Max Act: 10.8375. Min Act: -0.1700
Data Index: 340150 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.2750. Min Range: -11.2750
Max Act: 10.9000. Min Act: -0.1700
Data Index: 5011254 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.2750. Min Range: -11.2750
Max Act: 10.8375. Min Act: -0.1700
Data Index: 4726443 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.2750. Min Range: -11.2750
Max Act: 10.8375. Min Act: -0.1700
Data Index: 2758951 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.2750. Min Range: -11.2750
Max Act: 10.8375. Min Act: -0.1700
Data Index: 6229112 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #19