Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3706 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9111. Min Range: -3.9111
Max Act: 3.9111. Min Act: -0.1700
Data Index: 601378 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9111. Min Range: -3.9111
Max Act: 3.9111. Min Act: -0.1700
Data Index: 3033953 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9111. Min Range: -3.9111
Max Act: 3.7547. Min Act: -0.1700
Data Index: 3341844 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9111. Min Range: -3.9111
Max Act: 3.6921. Min Act: -0.1700
Data Index: 800720 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9111. Min Range: -3.9111
Max Act: 3.6921. Min Act: -0.1700
Data Index: 190686 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9111. Min Range: -3.9111
Max Act: 3.6921. Min Act: -0.1700
Data Index: 810645 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9111. Min Range: -3.9111
Max Act: 3.6452. Min Act: -0.1700
Data Index: 5954083 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9111. Min Range: -3.9111
Max Act: 3.6452. Min Act: -0.1700
Data Index: 1164315 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9111. Min Range: -3.9111
Max Act: 3.5826. Min Act: -0.1700
Data Index: 8334088 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9111. Min Range: -3.9111
Max Act: 3.5670. Min Act: -0.1700
Data Index: 8326391 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9111. Min Range: -3.9111
Max Act: 3.5670. Min Act: -0.1700
Data Index: 5722337 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9111. Min Range: -3.9111
Max Act: 3.5356. Min Act: -0.1700
Data Index: 661840 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9111. Min Range: -3.9111
Max Act: 3.5356. Min Act: -0.1700
Data Index: 6717534 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9111. Min Range: -3.9111
Max Act: 3.5356. Min Act: -0.1700
Data Index: 1820830 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9111. Min Range: -3.9111
Max Act: 3.5200. Min Act: -0.1700
Data Index: 7582948 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9111. Min Range: -3.9111
Max Act: 3.5200. Min Act: -0.1700
Data Index: 2764566 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9111. Min Range: -3.9111
Max Act: 3.5356. Min Act: -0.1700
Data Index: 3908334 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9111. Min Range: -3.9111
Max Act: 3.5356. Min Act: -0.1700
Data Index: 2650541 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9111. Min Range: -3.9111
Max Act: 3.5043. Min Act: -0.1700
Data Index: 2956332 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9111. Min Range: -3.9111
Max Act: 3.5043. Min Act: -0.1700
Data Index: 5260927 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #19