Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3677 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 0.9853. Min Range: -0.9853
Max Act: 0.9853. Min Act: -0.1694
Data Index: 6623482 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.9853. Min Range: -0.9853
Max Act: 0.9335. Min Act: -0.1696
Data Index: 5502712 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.9853. Min Range: -0.9853
Max Act: 0.9335. Min Act: -0.1700
Data Index: 3300206 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.9853. Min Range: -0.9853
Max Act: 0.9249. Min Act: -0.1699
Data Index: 7405941 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.9853. Min Range: -0.9853
Max Act: 0.9335. Min Act: -0.1698
Data Index: 8814105 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.9853. Min Range: -0.9853
Max Act: 0.9163. Min Act: -0.1696
Data Index: 2063511 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.9853. Min Range: -0.9853
Max Act: 0.9163. Min Act: -0.1700
Data Index: 4814152 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.9853. Min Range: -0.9853
Max Act: 0.9077. Min Act: -0.1696
Data Index: 8476947 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.9853. Min Range: -0.9853
Max Act: 0.8992. Min Act: -0.1698
Data Index: 7899525 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.9853. Min Range: -0.9853
Max Act: 0.9077. Min Act: -0.1692
Data Index: 484438 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.9853. Min Range: -0.9853
Max Act: 0.8992. Min Act: -0.1700
Data Index: 2065470 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.9853. Min Range: -0.9853
Max Act: 0.8821. Min Act: -0.1698
Data Index: 2431596 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.9853. Min Range: -0.9853
Max Act: 0.8821. Min Act: -0.1697
Data Index: 1320336 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.9853. Min Range: -0.9853
Max Act: 0.8821. Min Act: -0.1700
Data Index: 6502193 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.9853. Min Range: -0.9853
Max Act: 0.8821. Min Act: -0.1700
Data Index: 2805862 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.9853. Min Range: -0.9853
Max Act: 0.8736. Min Act: -0.1692
Data Index: 1371397 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.9853. Min Range: -0.9853
Max Act: 0.8651. Min Act: -0.1700
Data Index: 5774555 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.9853. Min Range: -0.9853
Max Act: 0.8736. Min Act: -0.1700
Data Index: 8728410 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.9853. Min Range: -0.9853
Max Act: 0.8736. Min Act: -0.1655
Data Index: 2001717 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.9853. Min Range: -0.9853
Max Act: 0.8736. Min Act: -0.1700
Data Index: 1513486 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19