Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3628 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.9574. Min Range: -3.9574
Max Act: 3.9574. Min Act: -0.1700
Data Index: 1866828 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9574. Min Range: -3.9574
Max Act: 3.8949. Min Act: -0.1700
Data Index: 218897 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9574. Min Range: -3.9574
Max Act: 3.8324. Min Act: -0.1700
Data Index: 2417768 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9574. Min Range: -3.9574
Max Act: 3.8636. Min Act: -0.1700
Data Index: 6783213 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9574. Min Range: -3.9574
Max Act: 3.8324. Min Act: -0.1700
Data Index: 3687722 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9574. Min Range: -3.9574
Max Act: 3.8011. Min Act: -0.1700
Data Index: 2641806 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9574. Min Range: -3.9574
Max Act: 3.7698. Min Act: -0.1700
Data Index: 4607193 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9574. Min Range: -3.9574
Max Act: 3.7698. Min Act: -0.1700
Data Index: 8572148 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9574. Min Range: -3.9574
Max Act: 3.7698. Min Act: -0.1700
Data Index: 8321731 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9574. Min Range: -3.9574
Max Act: 3.7698. Min Act: -0.1700
Data Index: 6217946 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9574. Min Range: -3.9574
Max Act: 3.7698. Min Act: -0.1700
Data Index: 5601430 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9574. Min Range: -3.9574
Max Act: 3.7698. Min Act: -0.1700
Data Index: 3826341 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9574. Min Range: -3.9574
Max Act: 3.7698. Min Act: -0.1700
Data Index: 1917676 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9574. Min Range: -3.9574
Max Act: 3.7698. Min Act: -0.1700
Data Index: 3562692 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9574. Min Range: -3.9574
Max Act: 3.7698. Min Act: -0.1700
Data Index: 1902017 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9574. Min Range: -3.9574
Max Act: 3.7698. Min Act: -0.1700
Data Index: 3019990 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9574. Min Range: -3.9574
Max Act: 3.7698. Min Act: -0.1700
Data Index: 1843585 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9574. Min Range: -3.9574
Max Act: 3.7385. Min Act: -0.1700
Data Index: 2438943 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9574. Min Range: -3.9574
Max Act: 3.7385. Min Act: -0.1700
Data Index: 1356932 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9574. Min Range: -3.9574
Max Act: 3.7385. Min Act: -0.1700
Data Index: 1399242 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19