Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3657 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.0016. Min Range: -2.0016
Max Act: 2.0016. Min Act: -0.1700
Data Index: 1268131 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0016. Min Range: -2.0016
Max Act: 1.9168. Min Act: -0.1700
Data Index: 221592 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0016. Min Range: -2.0016
Max Act: 1.9168. Min Act: -0.1700
Data Index: 7654601 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0016. Min Range: -2.0016
Max Act: 1.9168. Min Act: -0.1700
Data Index: 7192531 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0016. Min Range: -2.0016
Max Act: 1.9168. Min Act: -0.1700
Data Index: 7847694 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0016. Min Range: -2.0016
Max Act: 1.8997. Min Act: -0.1700
Data Index: 3730625 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0016. Min Range: -2.0016
Max Act: 1.8997. Min Act: -0.1700
Data Index: 7690731 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0016. Min Range: -2.0016
Max Act: 1.8997. Min Act: -0.1700
Data Index: 7239483 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0016. Min Range: -2.0016
Max Act: 1.8997. Min Act: -0.1700
Data Index: 8347100 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0016. Min Range: -2.0016
Max Act: 1.8827. Min Act: -0.1700
Data Index: 922290 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0016. Min Range: -2.0016
Max Act: 1.8656. Min Act: -0.1700
Data Index: 882948 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0016. Min Range: -2.0016
Max Act: 1.8827. Min Act: -0.1700
Data Index: 1216064 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0016. Min Range: -2.0016
Max Act: 1.8656. Min Act: -0.1700
Data Index: 7209760 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0016. Min Range: -2.0016
Max Act: 1.8656. Min Act: -0.1700
Data Index: 6295767 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0016. Min Range: -2.0016
Max Act: 1.8656. Min Act: -0.1700
Data Index: 2147753 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0016. Min Range: -2.0016
Max Act: 1.8656. Min Act: -0.1700
Data Index: 6834080 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0016. Min Range: -2.0016
Max Act: 1.8656. Min Act: -0.1700
Data Index: 7622590 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0016. Min Range: -2.0016
Max Act: 1.8656. Min Act: -0.1693
Data Index: 6485265 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0016. Min Range: -2.0016
Max Act: 1.8485. Min Act: -0.1700
Data Index: 4242110 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0016. Min Range: -2.0016
Max Act: 1.8485. Min Act: -0.1700
Data Index: 4861104 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #19