Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4978 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2747. Min Range: -7.2747
Max Act: 7.2747. Min Act: -0.1700
Data Index: 3711325 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2747. Min Range: -7.2747
Max Act: 6.8372. Min Act: -0.1700
Data Index: 6168358 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2747. Min Range: -7.2747
Max Act: 6.8372. Min Act: -0.1700
Data Index: 94854 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2747. Min Range: -7.2747
Max Act: 6.5872. Min Act: -0.1700
Data Index: 4688848 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2747. Min Range: -7.2747
Max Act: 6.5247. Min Act: -0.1700
Data Index: 390418 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2747. Min Range: -7.2747
Max Act: 6.5247. Min Act: -0.1700
Data Index: 1601753 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2747. Min Range: -7.2747
Max Act: 6.4935. Min Act: -0.1700
Data Index: 7441338 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2747. Min Range: -7.2747
Max Act: 6.4622. Min Act: -0.1700
Data Index: 7713655 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2747. Min Range: -7.2747
Max Act: 6.4310. Min Act: -0.1700
Data Index: 3668689 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2747. Min Range: -7.2747
Max Act: 6.4310. Min Act: -0.1700
Data Index: 3033116 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2747. Min Range: -7.2747
Max Act: 6.4310. Min Act: -0.1700
Data Index: 3374082 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2747. Min Range: -7.2747
Max Act: 6.3997. Min Act: -0.1700
Data Index: 1391957 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2747. Min Range: -7.2747
Max Act: 6.3997. Min Act: -0.1700
Data Index: 6650309 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2747. Min Range: -7.2747
Max Act: 6.3685. Min Act: -0.1700
Data Index: 2119253 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2747. Min Range: -7.2747
Max Act: 6.3685. Min Act: -0.1700
Data Index: 6119641 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2747. Min Range: -7.2747
Max Act: 6.3685. Min Act: -0.1700
Data Index: 2443983 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2747. Min Range: -7.2747
Max Act: 6.3372. Min Act: -0.1700
Data Index: 5887132 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2747. Min Range: -7.2747
Max Act: 6.3372. Min Act: -0.1700
Data Index: 2646439 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2747. Min Range: -7.2747
Max Act: 6.3060. Min Act: -0.1700
Data Index: 5505923 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2747. Min Range: -7.2747
Max Act: 6.3060. Min Act: -0.1700
Data Index: 6435120 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #19