Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 45 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.0524. Min Range: -2.0524
Max Act: 2.0524. Min Act: -0.1700
Data Index: 4413443 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0524. Min Range: -2.0524
Max Act: 2.0187. Min Act: -0.1700
Data Index: 3357920 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0524. Min Range: -2.0524
Max Act: 2.0187. Min Act: -0.1700
Data Index: 8380610 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0524. Min Range: -2.0524
Max Act: 2.0019. Min Act: -0.1700
Data Index: 5886322 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0524. Min Range: -2.0524
Max Act: 1.9511. Min Act: -0.1700
Data Index: 3328280 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0524. Min Range: -2.0524
Max Act: 1.9511. Min Act: -0.1700
Data Index: 842740 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0524. Min Range: -2.0524
Max Act: 1.9341. Min Act: -0.1700
Data Index: 8506558 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0524. Min Range: -2.0524
Max Act: 1.9341. Min Act: -0.1700
Data Index: 4519068 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0524. Min Range: -2.0524
Max Act: 1.9170. Min Act: -0.1700
Data Index: 5527751 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0524. Min Range: -2.0524
Max Act: 1.9170. Min Act: -0.1700
Data Index: 2154960 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0524. Min Range: -2.0524
Max Act: 1.9170. Min Act: -0.1700
Data Index: 462441 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0524. Min Range: -2.0524
Max Act: 1.9000. Min Act: -0.1700
Data Index: 5334135 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0524. Min Range: -2.0524
Max Act: 1.8829. Min Act: -0.1700
Data Index: 6758498 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0524. Min Range: -2.0524
Max Act: 1.8829. Min Act: -0.1700
Data Index: 1758317 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0524. Min Range: -2.0524
Max Act: 1.8829. Min Act: -0.1696
Data Index: 7817926 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0524. Min Range: -2.0524
Max Act: 1.8829. Min Act: -0.1700
Data Index: 7625058 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0524. Min Range: -2.0524
Max Act: 1.8829. Min Act: -0.1700
Data Index: 2244532 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0524. Min Range: -2.0524
Max Act: 1.8658. Min Act: -0.1700
Data Index: 4605231 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0524. Min Range: -2.0524
Max Act: 1.8658. Min Act: -0.1700
Data Index: 4089858 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0524. Min Range: -2.0524
Max Act: 1.8658. Min Act: -0.1700
Data Index: 4352266 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19