Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4988 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5889. Min Range: -4.5889
Max Act: 4.5889. Min Act: -0.1700
Data Index: 1259439 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5889. Min Range: -4.5889
Max Act: 4.5889. Min Act: -0.1700
Data Index: 1489242 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5889. Min Range: -4.5889
Max Act: 4.4327. Min Act: -0.1700
Data Index: 5255088 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5889. Min Range: -4.5889
Max Act: 4.4014. Min Act: -0.1700
Data Index: 4361508 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5889. Min Range: -4.5889
Max Act: 4.4014. Min Act: -0.1700
Data Index: 3090104 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5889. Min Range: -4.5889
Max Act: 4.3702. Min Act: -0.1700
Data Index: 8350146 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5889. Min Range: -4.5889
Max Act: 4.3389. Min Act: -0.1700
Data Index: 6550039 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5889. Min Range: -4.5889
Max Act: 4.3389. Min Act: -0.1700
Data Index: 3716743 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5889. Min Range: -4.5889
Max Act: 4.3389. Min Act: -0.1700
Data Index: 6735898 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5889. Min Range: -4.5889
Max Act: 4.3389. Min Act: -0.1700
Data Index: 2833985 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5889. Min Range: -4.5889
Max Act: 4.3076. Min Act: -0.1700
Data Index: 7826894 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5889. Min Range: -4.5889
Max Act: 4.3076. Min Act: -0.1700
Data Index: 3581 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5889. Min Range: -4.5889
Max Act: 4.3076. Min Act: -0.1700
Data Index: 113322 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5889. Min Range: -4.5889
Max Act: 4.2764. Min Act: -0.1700
Data Index: 4134151 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5889. Min Range: -4.5889
Max Act: 4.2764. Min Act: -0.1700
Data Index: 5385494 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5889. Min Range: -4.5889
Max Act: 4.2764. Min Act: -0.1700
Data Index: 3346217 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5889. Min Range: -4.5889
Max Act: 4.2764. Min Act: -0.1700
Data Index: 2394090 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5889. Min Range: -4.5889
Max Act: 4.2451. Min Act: -0.1700
Data Index: 6643417 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5889. Min Range: -4.5889
Max Act: 4.2764. Min Act: -0.1700
Data Index: 2068218 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5889. Min Range: -4.5889
Max Act: 4.2139. Min Act: -0.1700
Data Index: 1551877 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #19