Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 927 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.5683. Min Range: -5.5683
Max Act: 5.5683. Min Act: -0.1700
Data Index: 1223117 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5683. Min Range: -5.5683
Max Act: 5.5683. Min Act: -0.1700
Data Index: 1392122 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5683. Min Range: -5.5683
Max Act: 5.5683. Min Act: -0.1700
Data Index: 107256 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5683. Min Range: -5.5683
Max Act: 5.5683. Min Act: -0.1700
Data Index: 275219 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5683. Min Range: -5.5683
Max Act: 5.5683. Min Act: -0.1700
Data Index: 1387824 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5683. Min Range: -5.5683
Max Act: 5.5683. Min Act: -0.1700
Data Index: 1663699 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5683. Min Range: -5.5683
Max Act: 5.5683. Min Act: -0.1700
Data Index: 389652 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5683. Min Range: -5.5683
Max Act: 5.5683. Min Act: -0.1700
Data Index: 1511745 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5683. Min Range: -5.5683
Max Act: 5.5683. Min Act: -0.1700
Data Index: 2019485 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5683. Min Range: -5.5683
Max Act: 5.5683. Min Act: -0.1700
Data Index: 1246752 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5683. Min Range: -5.5683
Max Act: 5.5683. Min Act: -0.1700
Data Index: 1002464 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5683. Min Range: -5.5683
Max Act: 5.5683. Min Act: -0.1700
Data Index: 1427751 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5683. Min Range: -5.5683
Max Act: 5.5683. Min Act: -0.1700
Data Index: 165288 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5683. Min Range: -5.5683
Max Act: 5.5683. Min Act: -0.1700
Data Index: 1970836 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5683. Min Range: -5.5683
Max Act: 5.5683. Min Act: -0.1700
Data Index: 1946473 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5683. Min Range: -5.5683
Max Act: 5.5683. Min Act: -0.1700
Data Index: 1195689 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5683. Min Range: -5.5683
Max Act: 5.5683. Min Act: -0.1700
Data Index: 1125739 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5683. Min Range: -5.5683
Max Act: 5.5683. Min Act: -0.1700
Data Index: 93824 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5683. Min Range: -5.5683
Max Act: 5.5683. Min Act: -0.1700
Data Index: 475593 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5683. Min Range: -5.5683
Max Act: 5.5683. Min Act: -0.1700
Data Index: 1790325 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #19