Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1556 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5412. Min Range: -8.5412
Max Act: 8.5412. Min Act: -0.1700
Data Index: 3336194 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5412. Min Range: -8.5412
Max Act: 8.4787. Min Act: -0.1700
Data Index: 1860732 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5412. Min Range: -8.5412
Max Act: 8.4162. Min Act: -0.1700
Data Index: 3212520 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5412. Min Range: -8.5412
Max Act: 8.3537. Min Act: -0.1700
Data Index: 6839331 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5412. Min Range: -8.5412
Max Act: 8.2912. Min Act: -0.1700
Data Index: 2396806 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5412. Min Range: -8.5412
Max Act: 8.2912. Min Act: -0.1700
Data Index: 277211 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5412. Min Range: -8.5412
Max Act: 8.2912. Min Act: -0.1700
Data Index: 6841165 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5412. Min Range: -8.5412
Max Act: 8.0412. Min Act: -0.1700
Data Index: 1044345 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5412. Min Range: -8.5412
Max Act: 8.0412. Min Act: -0.1700
Data Index: 1020666 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5412. Min Range: -8.5412
Max Act: 8.0412. Min Act: -0.1700
Data Index: 8352129 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5412. Min Range: -8.5412
Max Act: 7.9787. Min Act: -0.1700
Data Index: 5446202 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5412. Min Range: -8.5412
Max Act: 7.9787. Min Act: -0.1700
Data Index: 8177560 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5412. Min Range: -8.5412
Max Act: 7.9787. Min Act: -0.1700
Data Index: 8548457 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5412. Min Range: -8.5412
Max Act: 7.9162. Min Act: -0.1700
Data Index: 6833410 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5412. Min Range: -8.5412
Max Act: 7.9162. Min Act: -0.1700
Data Index: 6833184 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5412. Min Range: -8.5412
Max Act: 7.9162. Min Act: -0.1700
Data Index: 5703363 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5412. Min Range: -8.5412
Max Act: 7.9162. Min Act: -0.1700
Data Index: 6338852 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5412. Min Range: -8.5412
Max Act: 7.8537. Min Act: -0.1700
Data Index: 6402373 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5412. Min Range: -8.5412
Max Act: 7.8537. Min Act: -0.1700
Data Index: 820605 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5412. Min Range: -8.5412
Max Act: 7.8537. Min Act: -0.1700
Data Index: 2801485 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #19