Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 584 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.8696. Min Range: -3.8696
Max Act: 3.8696. Min Act: -0.1700
Data Index: 1006217 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8696. Min Range: -3.8696
Max Act: 3.8696. Min Act: -0.1700
Data Index: 7037870 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8696. Min Range: -3.8696
Max Act: 3.8383. Min Act: -0.1700
Data Index: 7013294 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8696. Min Range: -3.8696
Max Act: 3.8383. Min Act: -0.1700
Data Index: 7804242 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8696. Min Range: -3.8696
Max Act: 3.8383. Min Act: -0.1700
Data Index: 7371082 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8696. Min Range: -3.8696
Max Act: 3.7758. Min Act: -0.1700
Data Index: 3123228 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8696. Min Range: -3.8696
Max Act: 3.8070. Min Act: -0.1700
Data Index: 7664456 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8696. Min Range: -3.8696
Max Act: 3.8070. Min Act: -0.1700
Data Index: 1361604 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8696. Min Range: -3.8696
Max Act: 3.8070. Min Act: -0.1700
Data Index: 6075661 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8696. Min Range: -3.8696
Max Act: 3.8070. Min Act: -0.1700
Data Index: 2398743 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8696. Min Range: -3.8696
Max Act: 3.8070. Min Act: -0.1700
Data Index: 3474095 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8696. Min Range: -3.8696
Max Act: 3.8070. Min Act: -0.1700
Data Index: 5894290 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8696. Min Range: -3.8696
Max Act: 3.7758. Min Act: -0.1700
Data Index: 5853089 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8696. Min Range: -3.8696
Max Act: 3.8070. Min Act: -0.1698
Data Index: 5435185 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8696. Min Range: -3.8696
Max Act: 3.8070. Min Act: -0.1700
Data Index: 7172131 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8696. Min Range: -3.8696
Max Act: 3.8070. Min Act: -0.1700
Data Index: 1841085 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8696. Min Range: -3.8696
Max Act: 3.8070. Min Act: -0.1700
Data Index: 1119603 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8696. Min Range: -3.8696
Max Act: 3.8070. Min Act: -0.1700
Data Index: 4703670 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8696. Min Range: -3.8696
Max Act: 3.8070. Min Act: -0.1700
Data Index: 3235515 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8696. Min Range: -3.8696
Max Act: 3.7758. Min Act: -0.1700
Data Index: 4520561 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19