Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1545 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.9784. Min Range: -1.9784
Max Act: 1.9784. Min Act: -0.1700
Data Index: 4770551 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9784. Min Range: -1.9784
Max Act: 1.9275. Min Act: -0.1700
Data Index: 3592043 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9784. Min Range: -1.9784
Max Act: 1.9275. Min Act: -0.1700
Data Index: 4810425 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9784. Min Range: -1.9784
Max Act: 1.9275. Min Act: -0.1700
Data Index: 4475377 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9784. Min Range: -1.9784
Max Act: 1.9104. Min Act: -0.1700
Data Index: 4132787 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9784. Min Range: -1.9784
Max Act: 1.8934. Min Act: -0.1700
Data Index: 62033 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9784. Min Range: -1.9784
Max Act: 1.8421. Min Act: -0.1700
Data Index: 5922933 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9784. Min Range: -1.9784
Max Act: 1.8421. Min Act: -0.1700
Data Index: 6849147 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9784. Min Range: -1.9784
Max Act: 1.8421. Min Act: -0.1700
Data Index: 6736260 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9784. Min Range: -1.9784
Max Act: 1.8421. Min Act: -0.1700
Data Index: 1136329 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9784. Min Range: -1.9784
Max Act: 1.8249. Min Act: -0.1700
Data Index: 3760180 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9784. Min Range: -1.9784
Max Act: 1.8249. Min Act: -0.1700
Data Index: 623897 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9784. Min Range: -1.9784
Max Act: 1.8249. Min Act: -0.1700
Data Index: 1919942 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9784. Min Range: -1.9784
Max Act: 1.8077. Min Act: -0.1700
Data Index: 6056491 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9784. Min Range: -1.9784
Max Act: 1.8249. Min Act: -0.1700
Data Index: 5771735 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9784. Min Range: -1.9784
Max Act: 1.8077. Min Act: -0.1700
Data Index: 733614 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9784. Min Range: -1.9784
Max Act: 1.8077. Min Act: -0.1700
Data Index: 1815082 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9784. Min Range: -1.9784
Max Act: 1.8077. Min Act: -0.1700
Data Index: 605405 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9784. Min Range: -1.9784
Max Act: 1.7905. Min Act: -0.1700
Data Index: 3369639 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9784. Min Range: -1.9784
Max Act: 1.8077. Min Act: -0.1700
Data Index: 240257 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19