Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1480 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 9.4072. Min Range: -9.4072
Max Act: 9.4072. Min Act: -0.1700
Data Index: 687023 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4072. Min Range: -9.4072
Max Act: 9.2822. Min Act: -0.1700
Data Index: 5564005 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4072. Min Range: -9.4072
Max Act: 9.1572. Min Act: -0.1700
Data Index: 4541125 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4072. Min Range: -9.4072
Max Act: 9.0322. Min Act: -0.1700
Data Index: 6163017 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4072. Min Range: -9.4072
Max Act: 8.9697. Min Act: -0.1700
Data Index: 802810 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4072. Min Range: -9.4072
Max Act: 8.9697. Min Act: -0.1700
Data Index: 7357199 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4072. Min Range: -9.4072
Max Act: 8.8447. Min Act: -0.1700
Data Index: 1587415 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4072. Min Range: -9.4072
Max Act: 8.8447. Min Act: -0.1700
Data Index: 2563789 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4072. Min Range: -9.4072
Max Act: 8.8447. Min Act: -0.1700
Data Index: 1688090 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4072. Min Range: -9.4072
Max Act: 8.7822. Min Act: -0.1700
Data Index: 4199295 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4072. Min Range: -9.4072
Max Act: 8.8447. Min Act: -0.1700
Data Index: 2937220 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4072. Min Range: -9.4072
Max Act: 8.7822. Min Act: -0.1700
Data Index: 2661562 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4072. Min Range: -9.4072
Max Act: 8.7197. Min Act: -0.1700
Data Index: 6341991 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4072. Min Range: -9.4072
Max Act: 8.7197. Min Act: -0.1700
Data Index: 5883784 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4072. Min Range: -9.4072
Max Act: 8.6572. Min Act: -0.1700
Data Index: 2642659 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4072. Min Range: -9.4072
Max Act: 8.7197. Min Act: -0.1700
Data Index: 3619644 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4072. Min Range: -9.4072
Max Act: 8.6572. Min Act: -0.1700
Data Index: 8745808 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4072. Min Range: -9.4072
Max Act: 8.6572. Min Act: -0.1700
Data Index: 4741643 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4072. Min Range: -9.4072
Max Act: 8.6572. Min Act: -0.1700
Data Index: 5122736 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4072. Min Range: -9.4072
Max Act: 8.5947. Min Act: -0.1700
Data Index: 2883597 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #19