Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3957 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7662. Min Range: -5.7662
Max Act: 5.7662. Min Act: -0.1700
Data Index: 7950969 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7662. Min Range: -5.7662
Max Act: 5.6724. Min Act: -0.1700
Data Index: 8081989 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7662. Min Range: -5.7662
Max Act: 5.6724. Min Act: -0.1700
Data Index: 8380866 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7662. Min Range: -5.7662
Max Act: 5.5787. Min Act: -0.1700
Data Index: 7293012 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7662. Min Range: -5.7662
Max Act: 5.6099. Min Act: -0.1700
Data Index: 64139 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7662. Min Range: -5.7662
Max Act: 5.5474. Min Act: -0.1700
Data Index: 942924 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7662. Min Range: -5.7662
Max Act: 5.5162. Min Act: -0.1700
Data Index: 4157791 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7662. Min Range: -5.7662
Max Act: 5.4537. Min Act: -0.1700
Data Index: 6568937 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7662. Min Range: -5.7662
Max Act: 5.4537. Min Act: -0.1700
Data Index: 2345416 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7662. Min Range: -5.7662
Max Act: 5.4537. Min Act: -0.1700
Data Index: 565406 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7662. Min Range: -5.7662
Max Act: 5.4224. Min Act: -0.1700
Data Index: 5352930 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7662. Min Range: -5.7662
Max Act: 5.4224. Min Act: -0.1700
Data Index: 3770138 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7662. Min Range: -5.7662
Max Act: 5.4224. Min Act: -0.1700
Data Index: 5978022 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7662. Min Range: -5.7662
Max Act: 5.4224. Min Act: -0.1700
Data Index: 1823424 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7662. Min Range: -5.7662
Max Act: 5.3912. Min Act: -0.1700
Data Index: 2362286 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7662. Min Range: -5.7662
Max Act: 5.3912. Min Act: -0.1700
Data Index: 6523946 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7662. Min Range: -5.7662
Max Act: 5.3912. Min Act: -0.1700
Data Index: 3151227 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7662. Min Range: -5.7662
Max Act: 5.3599. Min Act: -0.1700
Data Index: 1196551 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7662. Min Range: -5.7662
Max Act: 5.3912. Min Act: -0.1700
Data Index: 839940 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7662. Min Range: -5.7662
Max Act: 5.3599. Min Act: -0.1700
Data Index: 4265540 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #19