Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4953 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5970. Min Range: -8.5970
Max Act: 8.5970. Min Act: -0.1700
Data Index: 6464988 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5970. Min Range: -8.5970
Max Act: 8.2845. Min Act: -0.1700
Data Index: 7914742 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5970. Min Range: -8.5970
Max Act: 8.1595. Min Act: -0.1700
Data Index: 8022083 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5970. Min Range: -8.5970
Max Act: 8.0970. Min Act: -0.1700
Data Index: 7783778 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5970. Min Range: -8.5970
Max Act: 8.0345. Min Act: -0.1700
Data Index: 8175526 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5970. Min Range: -8.5970
Max Act: 8.0345. Min Act: -0.1700
Data Index: 2763650 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5970. Min Range: -8.5970
Max Act: 8.0345. Min Act: -0.1700
Data Index: 2359519 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5970. Min Range: -8.5970
Max Act: 7.9095. Min Act: -0.1700
Data Index: 3957337 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5970. Min Range: -8.5970
Max Act: 7.9095. Min Act: -0.1700
Data Index: 4039808 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5970. Min Range: -8.5970
Max Act: 7.8470. Min Act: -0.1700
Data Index: 7273902 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5970. Min Range: -8.5970
Max Act: 7.8470. Min Act: -0.1700
Data Index: 7610657 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5970. Min Range: -8.5970
Max Act: 7.7845. Min Act: -0.1700
Data Index: 7451286 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5970. Min Range: -8.5970
Max Act: 7.7845. Min Act: -0.1700
Data Index: 661409 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5970. Min Range: -8.5970
Max Act: 7.7845. Min Act: -0.1700
Data Index: 2554382 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5970. Min Range: -8.5970
Max Act: 7.7845. Min Act: -0.1700
Data Index: 4226215 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5970. Min Range: -8.5970
Max Act: 7.7220. Min Act: -0.1700
Data Index: 3799813 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5970. Min Range: -8.5970
Max Act: 7.6595. Min Act: -0.1700
Data Index: 5223461 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5970. Min Range: -8.5970
Max Act: 7.5970. Min Act: -0.1700
Data Index: 6984197 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5970. Min Range: -8.5970
Max Act: 7.5970. Min Act: -0.1700
Data Index: 5944800 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5970. Min Range: -8.5970
Max Act: 7.5345. Min Act: -0.1700
Data Index: 593097 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #19