Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3606 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4205. Min Range: -5.4205
Max Act: 5.4205. Min Act: -0.1700
Data Index: 3661216 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4205. Min Range: -5.4205
Max Act: 5.2642. Min Act: -0.1700
Data Index: 4138919 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4205. Min Range: -5.4205
Max Act: 5.2642. Min Act: -0.1700
Data Index: 1758402 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4205. Min Range: -5.4205
Max Act: 5.2330. Min Act: -0.1700
Data Index: 1574771 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4205. Min Range: -5.4205
Max Act: 5.2330. Min Act: -0.1698
Data Index: 4132374 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4205. Min Range: -5.4205
Max Act: 5.2330. Min Act: -0.1700
Data Index: 5505920 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4205. Min Range: -5.4205
Max Act: 5.2017. Min Act: -0.1699
Data Index: 8586805 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4205. Min Range: -5.4205
Max Act: 5.2017. Min Act: -0.1700
Data Index: 5123106 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4205. Min Range: -5.4205
Max Act: 5.1705. Min Act: -0.1700
Data Index: 8516046 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4205. Min Range: -5.4205
Max Act: 5.1705. Min Act: -0.1700
Data Index: 886609 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4205. Min Range: -5.4205
Max Act: 5.1705. Min Act: -0.1700
Data Index: 6866496 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4205. Min Range: -5.4205
Max Act: 5.1705. Min Act: -0.1700
Data Index: 7758370 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4205. Min Range: -5.4205
Max Act: 5.1705. Min Act: -0.1699
Data Index: 7118125 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4205. Min Range: -5.4205
Max Act: 5.1392. Min Act: -0.1700
Data Index: 4939379 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4205. Min Range: -5.4205
Max Act: 5.1392. Min Act: -0.1700
Data Index: 1352533 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4205. Min Range: -5.4205
Max Act: 5.1080. Min Act: -0.1700
Data Index: 1038546 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4205. Min Range: -5.4205
Max Act: 5.1080. Min Act: -0.1700
Data Index: 2137559 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4205. Min Range: -5.4205
Max Act: 5.1080. Min Act: -0.1700
Data Index: 6851401 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4205. Min Range: -5.4205
Max Act: 5.1080. Min Act: -0.1700
Data Index: 8532195 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4205. Min Range: -5.4205
Max Act: 5.1080. Min Act: -0.1700
Data Index: 3002526 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19