Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2583 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6880. Min Range: -8.6880
Max Act: 8.6880. Min Act: -0.1700
Data Index: 2624826 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6880. Min Range: -8.6880
Max Act: 8.2505. Min Act: -0.1700
Data Index: 1138368 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6880. Min Range: -8.6880
Max Act: 8.0630. Min Act: -0.1700
Data Index: 5988078 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6880. Min Range: -8.6880
Max Act: 8.0630. Min Act: -0.1700
Data Index: 8004523 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6880. Min Range: -8.6880
Max Act: 8.0005. Min Act: -0.1700
Data Index: 503759 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6880. Min Range: -8.6880
Max Act: 8.0005. Min Act: -0.1700
Data Index: 4080953 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6880. Min Range: -8.6880
Max Act: 7.9380. Min Act: -0.1700
Data Index: 2501595 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6880. Min Range: -8.6880
Max Act: 7.8130. Min Act: -0.1700
Data Index: 4949554 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6880. Min Range: -8.6880
Max Act: 7.8755. Min Act: -0.1700
Data Index: 4059554 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6880. Min Range: -8.6880
Max Act: 7.8130. Min Act: -0.1700
Data Index: 902998 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6880. Min Range: -8.6880
Max Act: 7.7505. Min Act: -0.1700
Data Index: 933176 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6880. Min Range: -8.6880
Max Act: 7.7505. Min Act: -0.1700
Data Index: 1573309 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6880. Min Range: -8.6880
Max Act: 7.6255. Min Act: -0.1700
Data Index: 2116734 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6880. Min Range: -8.6880
Max Act: 7.8130. Min Act: -0.1700
Data Index: 582145 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6880. Min Range: -8.6880
Max Act: 7.6880. Min Act: -0.1700
Data Index: 4185620 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6880. Min Range: -8.6880
Max Act: 7.7505. Min Act: -0.1700
Data Index: 3713384 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6880. Min Range: -8.6880
Max Act: 7.6880. Min Act: -0.1700
Data Index: 7055449 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6880. Min Range: -8.6880
Max Act: 7.6880. Min Act: -0.1700
Data Index: 668788 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6880. Min Range: -8.6880
Max Act: 7.6880. Min Act: -0.1700
Data Index: 1952052 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6880. Min Range: -8.6880
Max Act: 7.6255. Min Act: -0.1700
Data Index: 5935483 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #19