Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2916 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7441. Min Range: -4.7441
Max Act: 4.7441. Min Act: -0.1700
Data Index: 1610111 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7441. Min Range: -4.7441
Max Act: 4.7129. Min Act: -0.1700
Data Index: 5645724 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7441. Min Range: -4.7441
Max Act: 4.6504. Min Act: -0.1700
Data Index: 1610126 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7441. Min Range: -4.7441
Max Act: 4.5879. Min Act: -0.1700
Data Index: 3904098 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7441. Min Range: -4.7441
Max Act: 4.5879. Min Act: -0.1700
Data Index: 5645732 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7441. Min Range: -4.7441
Max Act: 4.5879. Min Act: -0.1700
Data Index: 1844874 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7441. Min Range: -4.7441
Max Act: 4.5566. Min Act: -0.1700
Data Index: 8418270 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7441. Min Range: -4.7441
Max Act: 4.5566. Min Act: -0.1700
Data Index: 2696356 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7441. Min Range: -4.7441
Max Act: 4.5254. Min Act: -0.1700
Data Index: 1129380 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7441. Min Range: -4.7441
Max Act: 4.5254. Min Act: -0.1700
Data Index: 7051501 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7441. Min Range: -4.7441
Max Act: 4.4941. Min Act: -0.1700
Data Index: 5340085 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7441. Min Range: -4.7441
Max Act: 4.4941. Min Act: -0.1700
Data Index: 2489067 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7441. Min Range: -4.7441
Max Act: 4.4941. Min Act: -0.1700
Data Index: 589307 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7441. Min Range: -4.7441
Max Act: 4.4629. Min Act: -0.1700
Data Index: 6473306 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7441. Min Range: -4.7441
Max Act: 4.4629. Min Act: -0.1700
Data Index: 3169720 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7441. Min Range: -4.7441
Max Act: 4.4316. Min Act: -0.1700
Data Index: 5213786 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7441. Min Range: -4.7441
Max Act: 4.4316. Min Act: -0.1700
Data Index: 169100 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7441. Min Range: -4.7441
Max Act: 4.4316. Min Act: -0.1700
Data Index: 432307 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7441. Min Range: -4.7441
Max Act: 4.3691. Min Act: -0.1700
Data Index: 3956405 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7441. Min Range: -4.7441
Max Act: 4.4004. Min Act: -0.1700
Data Index: 6515710 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #19