Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5103 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.0562. Min Range: -10.0562
Max Act: 10.0562. Min Act: -0.1700
Data Index: 7424944 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.0562. Min Range: -10.0562
Max Act: 10.0562. Min Act: -0.1700
Data Index: 7424947 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.0562. Min Range: -10.0562
Max Act: 9.6812. Min Act: -0.1700
Data Index: 6684277 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.0562. Min Range: -10.0562
Max Act: 9.6187. Min Act: -0.1700
Data Index: 6925150 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.0562. Min Range: -10.0562
Max Act: 9.6187. Min Act: -0.1700
Data Index: 4845625 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.0562. Min Range: -10.0562
Max Act: 9.4937. Min Act: -0.1700
Data Index: 5700240 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.0562. Min Range: -10.0562
Max Act: 9.3062. Min Act: -0.1700
Data Index: 2816392 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.0562. Min Range: -10.0562
Max Act: 9.2437. Min Act: -0.1700
Data Index: 3880468 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.0562. Min Range: -10.0562
Max Act: 9.2437. Min Act: -0.1700
Data Index: 8598774 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.0562. Min Range: -10.0562
Max Act: 9.1812. Min Act: -0.1700
Data Index: 3239721 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.0562. Min Range: -10.0562
Max Act: 9.1812. Min Act: -0.1700
Data Index: 4126410 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.0562. Min Range: -10.0562
Max Act: 9.1812. Min Act: -0.1700
Data Index: 4868278 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.0562. Min Range: -10.0562
Max Act: 9.1812. Min Act: -0.1700
Data Index: 5961557 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.0562. Min Range: -10.0562
Max Act: 9.0562. Min Act: -0.1700
Data Index: 7311488 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.0562. Min Range: -10.0562
Max Act: 8.9937. Min Act: -0.1700
Data Index: 1929625 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.0562. Min Range: -10.0562
Max Act: 8.9937. Min Act: -0.1700
Data Index: 5983940 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.0562. Min Range: -10.0562
Max Act: 8.9937. Min Act: -0.1700
Data Index: 7911281 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.0562. Min Range: -10.0562
Max Act: 8.9312. Min Act: -0.1700
Data Index: 6476131 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.0562. Min Range: -10.0562
Max Act: 8.9312. Min Act: -0.1700
Data Index: 4488458 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.0562. Min Range: -10.0562
Max Act: 8.9312. Min Act: -0.1700
Data Index: 4185306 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #19