Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1475 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.9653. Min Range: -3.9653
Max Act: 3.9653. Min Act: -0.1700
Data Index: 445594 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9653. Min Range: -3.9653
Max Act: 3.9340. Min Act: -0.1700
Data Index: 8621102 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9653. Min Range: -3.9653
Max Act: 3.9340. Min Act: -0.1700
Data Index: 7467858 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9653. Min Range: -3.9653
Max Act: 3.9027. Min Act: -0.1700
Data Index: 7989250 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9653. Min Range: -3.9653
Max Act: 3.8715. Min Act: -0.1700
Data Index: 701533 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9653. Min Range: -3.9653
Max Act: 3.8715. Min Act: -0.1700
Data Index: 1855972 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9653. Min Range: -3.9653
Max Act: 3.8715. Min Act: -0.1700
Data Index: 1590962 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9653. Min Range: -3.9653
Max Act: 3.8402. Min Act: -0.1700
Data Index: 644090 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9653. Min Range: -3.9653
Max Act: 3.8402. Min Act: -0.1700
Data Index: 3078802 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9653. Min Range: -3.9653
Max Act: 3.8402. Min Act: -0.1700
Data Index: 378064 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9653. Min Range: -3.9653
Max Act: 3.8402. Min Act: -0.1700
Data Index: 2826104 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9653. Min Range: -3.9653
Max Act: 3.8402. Min Act: -0.1700
Data Index: 6631864 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9653. Min Range: -3.9653
Max Act: 3.8089. Min Act: -0.1700
Data Index: 1627671 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9653. Min Range: -3.9653
Max Act: 3.8402. Min Act: -0.1700
Data Index: 8051063 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9653. Min Range: -3.9653
Max Act: 3.8402. Min Act: -0.1700
Data Index: 803258 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9653. Min Range: -3.9653
Max Act: 3.8402. Min Act: -0.1700
Data Index: 3115255 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9653. Min Range: -3.9653
Max Act: 3.8089. Min Act: -0.1700
Data Index: 4467785 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9653. Min Range: -3.9653
Max Act: 3.8089. Min Act: -0.1700
Data Index: 6665907 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9653. Min Range: -3.9653
Max Act: 3.8089. Min Act: -0.1700
Data Index: 5746068 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9653. Min Range: -3.9653
Max Act: 3.8089. Min Act: -0.1700
Data Index: 2363897 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19