Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1234 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.0071. Min Range: -6.0071
Max Act: 6.0071. Min Act: -0.1700
Data Index: 7755692 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0071. Min Range: -6.0071
Max Act: 5.9446. Min Act: -0.1698
Data Index: 4170728 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0071. Min Range: -6.0071
Max Act: 5.8821. Min Act: -0.1700
Data Index: 5226774 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0071. Min Range: -6.0071
Max Act: 5.8821. Min Act: -0.1700
Data Index: 7563715 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0071. Min Range: -6.0071
Max Act: 5.8821. Min Act: -0.1700
Data Index: 5767259 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0071. Min Range: -6.0071
Max Act: 5.8196. Min Act: -0.1700
Data Index: 462997 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0071. Min Range: -6.0071
Max Act: 5.8509. Min Act: -0.1700
Data Index: 1650056 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0071. Min Range: -6.0071
Max Act: 5.8196. Min Act: -0.1692
Data Index: 4498048 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0071. Min Range: -6.0071
Max Act: 5.8196. Min Act: -0.1700
Data Index: 6760061 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0071. Min Range: -6.0071
Max Act: 5.7884. Min Act: -0.1693
Data Index: 302436 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0071. Min Range: -6.0071
Max Act: 5.7884. Min Act: -0.1700
Data Index: 4619966 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0071. Min Range: -6.0071
Max Act: 5.7884. Min Act: -0.1682
Data Index: 1954880 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0071. Min Range: -6.0071
Max Act: 5.7884. Min Act: -0.1697
Data Index: 8251477 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0071. Min Range: -6.0071
Max Act: 5.7259. Min Act: -0.1700
Data Index: 325336 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0071. Min Range: -6.0071
Max Act: 5.7259. Min Act: -0.1700
Data Index: 8228457 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0071. Min Range: -6.0071
Max Act: 5.7259. Min Act: -0.1690
Data Index: 6366482 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0071. Min Range: -6.0071
Max Act: 5.7259. Min Act: -0.1696
Data Index: 2559300 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0071. Min Range: -6.0071
Max Act: 5.6946. Min Act: -0.1693
Data Index: 3466121 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0071. Min Range: -6.0071
Max Act: 5.6634. Min Act: -0.1699
Data Index: 654795 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0071. Min Range: -6.0071
Max Act: 5.6946. Min Act: -0.1700
Data Index: 3559010 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #19