Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2611 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5009. Min Range: -5.5009
Max Act: 5.5009. Min Act: -0.1700
Data Index: 7761015 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5009. Min Range: -5.5009
Max Act: 5.2509. Min Act: -0.1700
Data Index: 5899070 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5009. Min Range: -5.5009
Max Act: 5.1571. Min Act: -0.1700
Data Index: 837770 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5009. Min Range: -5.5009
Max Act: 5.0946. Min Act: -0.1700
Data Index: 8325418 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5009. Min Range: -5.5009
Max Act: 5.0321. Min Act: -0.1700
Data Index: 1570782 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5009. Min Range: -5.5009
Max Act: 5.0321. Min Act: -0.1700
Data Index: 2174409 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5009. Min Range: -5.5009
Max Act: 5.0321. Min Act: -0.1700
Data Index: 3326868 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5009. Min Range: -5.5009
Max Act: 5.0009. Min Act: -0.1700
Data Index: 1982796 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5009. Min Range: -5.5009
Max Act: 4.9696. Min Act: -0.1700
Data Index: 3594616 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5009. Min Range: -5.5009
Max Act: 4.9071. Min Act: -0.1700
Data Index: 2607593 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5009. Min Range: -5.5009
Max Act: 4.9384. Min Act: -0.1700
Data Index: 5371811 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5009. Min Range: -5.5009
Max Act: 4.9696. Min Act: -0.1700
Data Index: 6597512 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5009. Min Range: -5.5009
Max Act: 4.9071. Min Act: -0.1700
Data Index: 7574784 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5009. Min Range: -5.5009
Max Act: 4.8759. Min Act: -0.1700
Data Index: 11332 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5009. Min Range: -5.5009
Max Act: 4.9071. Min Act: -0.1700
Data Index: 1697454 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5009. Min Range: -5.5009
Max Act: 4.8759. Min Act: -0.1700
Data Index: 333031 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5009. Min Range: -5.5009
Max Act: 4.8759. Min Act: -0.1700
Data Index: 3392941 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5009. Min Range: -5.5009
Max Act: 4.8759. Min Act: -0.1700
Data Index: 7727684 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5009. Min Range: -5.5009
Max Act: 4.8446. Min Act: -0.1700
Data Index: 8251982 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5009. Min Range: -5.5009
Max Act: 4.8134. Min Act: -0.1700
Data Index: 215998 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #19