Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5843 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3477. Min Range: -6.3477
Max Act: 6.3477. Min Act: -0.1700
Data Index: 2990744 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3477. Min Range: -6.3477
Max Act: 6.1915. Min Act: -0.1700
Data Index: 4714804 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3477. Min Range: -6.3477
Max Act: 6.1915. Min Act: -0.1700
Data Index: 6355209 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3477. Min Range: -6.3477
Max Act: 6.1602. Min Act: -0.1700
Data Index: 5065225 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3477. Min Range: -6.3477
Max Act: 6.0977. Min Act: -0.1700
Data Index: 6709279 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3477. Min Range: -6.3477
Max Act: 6.0977. Min Act: -0.1700
Data Index: 4464418 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3477. Min Range: -6.3477
Max Act: 6.0665. Min Act: -0.1700
Data Index: 6912500 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3477. Min Range: -6.3477
Max Act: 6.0352. Min Act: -0.1700
Data Index: 7958523 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3477. Min Range: -6.3477
Max Act: 6.0040. Min Act: -0.1700
Data Index: 7064069 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3477. Min Range: -6.3477
Max Act: 6.0040. Min Act: -0.1700
Data Index: 8098624 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3477. Min Range: -6.3477
Max Act: 6.0040. Min Act: -0.1700
Data Index: 8753619 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3477. Min Range: -6.3477
Max Act: 6.0040. Min Act: -0.1700
Data Index: 4071074 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3477. Min Range: -6.3477
Max Act: 6.0352. Min Act: -0.1700
Data Index: 6557695 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3477. Min Range: -6.3477
Max Act: 6.0040. Min Act: -0.1700
Data Index: 379925 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3477. Min Range: -6.3477
Max Act: 6.0352. Min Act: -0.1700
Data Index: 4864102 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3477. Min Range: -6.3477
Max Act: 5.9415. Min Act: -0.1700
Data Index: 1535151 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3477. Min Range: -6.3477
Max Act: 5.9415. Min Act: -0.1700
Data Index: 1178744 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3477. Min Range: -6.3477
Max Act: 6.0040. Min Act: -0.1700
Data Index: 6363504 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3477. Min Range: -6.3477
Max Act: 5.9727. Min Act: -0.1700
Data Index: 1561037 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3477. Min Range: -6.3477
Max Act: 5.9727. Min Act: -0.1700
Data Index: 5594974 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #19