Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3946 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8455. Min Range: -6.8455
Max Act: 6.8455. Min Act: -0.1700
Data Index: 5642464 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8455. Min Range: -6.8455
Max Act: 6.6580. Min Act: -0.1700
Data Index: 1109532 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8455. Min Range: -6.8455
Max Act: 6.6268. Min Act: -0.1700
Data Index: 6805500 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8455. Min Range: -6.8455
Max Act: 6.6268. Min Act: -0.1700
Data Index: 7358421 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8455. Min Range: -6.8455
Max Act: 6.5955. Min Act: -0.1700
Data Index: 2409318 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8455. Min Range: -6.8455
Max Act: 6.5643. Min Act: -0.1700
Data Index: 3683490 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8455. Min Range: -6.8455
Max Act: 6.5643. Min Act: -0.1700
Data Index: 815369 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8455. Min Range: -6.8455
Max Act: 6.5330. Min Act: -0.1700
Data Index: 5926535 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8455. Min Range: -6.8455
Max Act: 6.5643. Min Act: -0.1700
Data Index: 4721824 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8455. Min Range: -6.8455
Max Act: 6.5643. Min Act: -0.1700
Data Index: 3315526 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8455. Min Range: -6.8455
Max Act: 6.5643. Min Act: -0.1700
Data Index: 6195746 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8455. Min Range: -6.8455
Max Act: 6.5330. Min Act: -0.1700
Data Index: 3632453 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8455. Min Range: -6.8455
Max Act: 6.5330. Min Act: -0.1700
Data Index: 5160440 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8455. Min Range: -6.8455
Max Act: 6.5330. Min Act: -0.1700
Data Index: 2895973 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8455. Min Range: -6.8455
Max Act: 6.5330. Min Act: -0.1700
Data Index: 1834414 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8455. Min Range: -6.8455
Max Act: 6.5330. Min Act: -0.1700
Data Index: 5276734 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8455. Min Range: -6.8455
Max Act: 6.5018. Min Act: -0.1700
Data Index: 4315556 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8455. Min Range: -6.8455
Max Act: 6.5018. Min Act: -0.1700
Data Index: 212212 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8455. Min Range: -6.8455
Max Act: 6.5018. Min Act: -0.1699
Data Index: 4812899 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8455. Min Range: -6.8455
Max Act: 6.5018. Min Act: -0.1700
Data Index: 7054976 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #19