Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6376 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7857. Min Range: -5.7857
Max Act: 5.7857. Min Act: -0.1700
Data Index: 3935492 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7857. Min Range: -5.7857
Max Act: 5.6919. Min Act: -0.1700
Data Index: 1817694 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7857. Min Range: -5.7857
Max Act: 5.6607. Min Act: -0.1700
Data Index: 6799302 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7857. Min Range: -5.7857
Max Act: 5.5982. Min Act: -0.1700
Data Index: 1814996 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7857. Min Range: -5.7857
Max Act: 5.5982. Min Act: -0.1700
Data Index: 3640996 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7857. Min Range: -5.7857
Max Act: 5.5669. Min Act: -0.1700
Data Index: 4405897 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7857. Min Range: -5.7857
Max Act: 5.5044. Min Act: -0.1700
Data Index: 6304561 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7857. Min Range: -5.7857
Max Act: 5.5044. Min Act: -0.1700
Data Index: 3451418 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7857. Min Range: -5.7857
Max Act: 5.5044. Min Act: -0.1700
Data Index: 8518518 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7857. Min Range: -5.7857
Max Act: 5.5044. Min Act: -0.1700
Data Index: 2976788 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7857. Min Range: -5.7857
Max Act: 5.4732. Min Act: -0.1700
Data Index: 916096 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7857. Min Range: -5.7857
Max Act: 5.4732. Min Act: -0.1700
Data Index: 3190407 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7857. Min Range: -5.7857
Max Act: 5.4732. Min Act: -0.1700
Data Index: 951998 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7857. Min Range: -5.7857
Max Act: 5.4732. Min Act: -0.1700
Data Index: 18204 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7857. Min Range: -5.7857
Max Act: 5.4732. Min Act: -0.1700
Data Index: 8115101 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7857. Min Range: -5.7857
Max Act: 5.4419. Min Act: -0.1700
Data Index: 5607120 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7857. Min Range: -5.7857
Max Act: 5.4419. Min Act: -0.1700
Data Index: 5406889 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7857. Min Range: -5.7857
Max Act: 5.4107. Min Act: -0.1700
Data Index: 8727117 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7857. Min Range: -5.7857
Max Act: 5.4419. Min Act: -0.1700
Data Index: 3918211 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7857. Min Range: -5.7857
Max Act: 5.3482. Min Act: -0.1700
Data Index: 2375420 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #19