Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4682 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.4556. Min Range: -4.4556
Max Act: 4.4556. Min Act: -0.1700
Data Index: 8378866 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4556. Min Range: -4.4556
Max Act: 4.4556. Min Act: -0.1700
Data Index: 7809566 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4556. Min Range: -4.4556
Max Act: 4.3931. Min Act: -0.1700
Data Index: 1703148 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4556. Min Range: -4.4556
Max Act: 4.3618. Min Act: -0.1700
Data Index: 8376313 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4556. Min Range: -4.4556
Max Act: 4.3618. Min Act: -0.1700
Data Index: 5210503 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4556. Min Range: -4.4556
Max Act: 4.2993. Min Act: -0.1700
Data Index: 6273953 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4556. Min Range: -4.4556
Max Act: 4.3306. Min Act: -0.1700
Data Index: 1864088 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4556. Min Range: -4.4556
Max Act: 4.2993. Min Act: -0.1700
Data Index: 2885166 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4556. Min Range: -4.4556
Max Act: 4.2993. Min Act: -0.1700
Data Index: 594288 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4556. Min Range: -4.4556
Max Act: 4.2993. Min Act: -0.1700
Data Index: 907768 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4556. Min Range: -4.4556
Max Act: 4.2993. Min Act: -0.1700
Data Index: 4711181 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4556. Min Range: -4.4556
Max Act: 4.2993. Min Act: -0.1700
Data Index: 2420065 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4556. Min Range: -4.4556
Max Act: 4.2681. Min Act: -0.1700
Data Index: 7949238 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4556. Min Range: -4.4556
Max Act: 4.2681. Min Act: -0.1700
Data Index: 696083 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4556. Min Range: -4.4556
Max Act: 4.2368. Min Act: -0.1700
Data Index: 2087445 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4556. Min Range: -4.4556
Max Act: 4.2368. Min Act: -0.1700
Data Index: 7567294 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4556. Min Range: -4.4556
Max Act: 4.2368. Min Act: -0.1700
Data Index: 5354335 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4556. Min Range: -4.4556
Max Act: 4.2368. Min Act: -0.1700
Data Index: 1966505 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4556. Min Range: -4.4556
Max Act: 4.2368. Min Act: -0.1700
Data Index: 8343290 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4556. Min Range: -4.4556
Max Act: 4.2368. Min Act: -0.1700
Data Index: 1481387 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #19