Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5494 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5257. Min Range: -3.5257
Max Act: 3.5257. Min Act: -0.1700
Data Index: 5153319 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5257. Min Range: -3.5257
Max Act: 3.3533. Min Act: -0.1700
Data Index: 1812628 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5257. Min Range: -3.5257
Max Act: 3.3533. Min Act: -0.1700
Data Index: 1015055 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5257. Min Range: -3.5257
Max Act: 3.3376. Min Act: -0.1700
Data Index: 7278810 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5257. Min Range: -3.5257
Max Act: 3.3219. Min Act: -0.1700
Data Index: 4894198 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5257. Min Range: -3.5257
Max Act: 3.3376. Min Act: -0.1700
Data Index: 2507446 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5257. Min Range: -3.5257
Max Act: 3.3062. Min Act: -0.1700
Data Index: 6989194 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5257. Min Range: -3.5257
Max Act: 3.3219. Min Act: -0.1700
Data Index: 1660001 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5257. Min Range: -3.5257
Max Act: 3.2905. Min Act: -0.1700
Data Index: 5587317 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5257. Min Range: -3.5257
Max Act: 3.3062. Min Act: -0.1700
Data Index: 2591047 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5257. Min Range: -3.5257
Max Act: 3.3062. Min Act: -0.1700
Data Index: 3884525 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5257. Min Range: -3.5257
Max Act: 3.3219. Min Act: -0.1700
Data Index: 4756760 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5257. Min Range: -3.5257
Max Act: 3.3062. Min Act: -0.1700
Data Index: 3221967 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5257. Min Range: -3.5257
Max Act: 3.2905. Min Act: -0.1700
Data Index: 2753665 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5257. Min Range: -3.5257
Max Act: 3.2905. Min Act: -0.1700
Data Index: 4686404 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5257. Min Range: -3.5257
Max Act: 3.2748. Min Act: -0.1700
Data Index: 4232935 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5257. Min Range: -3.5257
Max Act: 3.2905. Min Act: -0.1700
Data Index: 1202326 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5257. Min Range: -3.5257
Max Act: 3.2748. Min Act: -0.1700
Data Index: 7539043 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5257. Min Range: -3.5257
Max Act: 3.2748. Min Act: -0.1700
Data Index: 4009556 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5257. Min Range: -3.5257
Max Act: 3.2591. Min Act: -0.1700
Data Index: 4630702 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #19