Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4768 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2108. Min Range: -8.2108
Max Act: 8.2108. Min Act: -0.1698
Data Index: 2102040 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2108. Min Range: -8.2108
Max Act: 8.2108. Min Act: -0.1698
Data Index: 2565887 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2108. Min Range: -8.2108
Max Act: 8.2108. Min Act: -0.1700
Data Index: 1871032 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2108. Min Range: -8.2108
Max Act: 8.1483. Min Act: -0.1695
Data Index: 667695 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2108. Min Range: -8.2108
Max Act: 8.1483. Min Act: -0.1695
Data Index: 6772248 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2108. Min Range: -8.2108
Max Act: 8.1483. Min Act: -0.1660
Data Index: 7706519 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2108. Min Range: -8.2108
Max Act: 8.0858. Min Act: -0.1699
Data Index: 4089680 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2108. Min Range: -8.2108
Max Act: 8.0858. Min Act: -0.1700
Data Index: 630650 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2108. Min Range: -8.2108
Max Act: 8.0858. Min Act: -0.1700
Data Index: 571188 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2108. Min Range: -8.2108
Max Act: 8.0858. Min Act: -0.1669
Data Index: 1736184 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2108. Min Range: -8.2108
Max Act: 8.0858. Min Act: -0.1700
Data Index: 3765142 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2108. Min Range: -8.2108
Max Act: 8.0858. Min Act: -0.1696
Data Index: 3420904 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2108. Min Range: -8.2108
Max Act: 8.0858. Min Act: -0.1700
Data Index: 3283835 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2108. Min Range: -8.2108
Max Act: 8.0858. Min Act: -0.1700
Data Index: 3258569 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2108. Min Range: -8.2108
Max Act: 8.0858. Min Act: -0.1700
Data Index: 1385236 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2108. Min Range: -8.2108
Max Act: 8.0858. Min Act: -0.1696
Data Index: 3146254 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2108. Min Range: -8.2108
Max Act: 8.0858. Min Act: -0.1700
Data Index: 314210 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2108. Min Range: -8.2108
Max Act: 8.0858. Min Act: -0.1700
Data Index: 3091672 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2108. Min Range: -8.2108
Max Act: 8.0858. Min Act: -0.1700
Data Index: 1378615 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2108. Min Range: -8.2108
Max Act: 8.0858. Min Act: -0.1700
Data Index: 2586126 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #19