Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2331 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9234. Min Range: -8.9234
Max Act: 8.9234. Min Act: -0.1700
Data Index: 4459929 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9234. Min Range: -8.9234
Max Act: 8.5484. Min Act: -0.1700
Data Index: 6893415 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9234. Min Range: -8.9234
Max Act: 8.5484. Min Act: -0.1700
Data Index: 2213619 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9234. Min Range: -8.9234
Max Act: 8.4859. Min Act: -0.1700
Data Index: 1936152 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9234. Min Range: -8.9234
Max Act: 8.4859. Min Act: -0.1700
Data Index: 1602586 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9234. Min Range: -8.9234
Max Act: 8.4234. Min Act: -0.1700
Data Index: 4695706 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9234. Min Range: -8.9234
Max Act: 8.2984. Min Act: -0.1700
Data Index: 8737590 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9234. Min Range: -8.9234
Max Act: 8.2359. Min Act: -0.1700
Data Index: 7260616 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9234. Min Range: -8.9234
Max Act: 8.2047. Min Act: -0.1700
Data Index: 6979163 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9234. Min Range: -8.9234
Max Act: 8.2047. Min Act: -0.1700
Data Index: 3585208 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9234. Min Range: -8.9234
Max Act: 8.1422. Min Act: -0.1700
Data Index: 3784672 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9234. Min Range: -8.9234
Max Act: 8.1109. Min Act: -0.1700
Data Index: 6419779 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9234. Min Range: -8.9234
Max Act: 8.1109. Min Act: -0.1700
Data Index: 556096 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9234. Min Range: -8.9234
Max Act: 8.0484. Min Act: -0.1700
Data Index: 4349937 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9234. Min Range: -8.9234
Max Act: 8.0797. Min Act: -0.1700
Data Index: 5592131 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9234. Min Range: -8.9234
Max Act: 8.0797. Min Act: -0.1700
Data Index: 900659 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9234. Min Range: -8.9234
Max Act: 8.0484. Min Act: -0.1700
Data Index: 5758981 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9234. Min Range: -8.9234
Max Act: 8.0484. Min Act: -0.1700
Data Index: 8435741 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9234. Min Range: -8.9234
Max Act: 8.0484. Min Act: -0.1700
Data Index: 3479949 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9234. Min Range: -8.9234
Max Act: 8.0484. Min Act: -0.1700
Data Index: 2011632 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #19