Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4829 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8857. Min Range: -5.8857
Max Act: 5.8857. Min Act: -0.1700
Data Index: 569793 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8857. Min Range: -5.8857
Max Act: 5.7920. Min Act: -0.1700
Data Index: 2010483 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8857. Min Range: -5.8857
Max Act: 5.5107. Min Act: -0.1700
Data Index: 2950186 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8857. Min Range: -5.8857
Max Act: 5.5107. Min Act: -0.1700
Data Index: 5057694 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8857. Min Range: -5.8857
Max Act: 5.4795. Min Act: -0.1700
Data Index: 5572500 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8857. Min Range: -5.8857
Max Act: 5.4482. Min Act: -0.1700
Data Index: 2619710 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8857. Min Range: -5.8857
Max Act: 5.3545. Min Act: -0.1700
Data Index: 3672861 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8857. Min Range: -5.8857
Max Act: 5.3232. Min Act: -0.1700
Data Index: 7234757 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8857. Min Range: -5.8857
Max Act: 5.3232. Min Act: -0.1700
Data Index: 1030837 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8857. Min Range: -5.8857
Max Act: 5.3232. Min Act: -0.1700
Data Index: 313473 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8857. Min Range: -5.8857
Max Act: 5.2920. Min Act: -0.1700
Data Index: 4147350 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8857. Min Range: -5.8857
Max Act: 5.2607. Min Act: -0.1700
Data Index: 148036 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8857. Min Range: -5.8857
Max Act: 5.2607. Min Act: -0.1700
Data Index: 8593575 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8857. Min Range: -5.8857
Max Act: 5.2295. Min Act: -0.1700
Data Index: 5485567 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8857. Min Range: -5.8857
Max Act: 5.2295. Min Act: -0.1700
Data Index: 7841473 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8857. Min Range: -5.8857
Max Act: 5.2295. Min Act: -0.1700
Data Index: 4378073 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8857. Min Range: -5.8857
Max Act: 5.1982. Min Act: -0.1700
Data Index: 6632666 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8857. Min Range: -5.8857
Max Act: 5.1982. Min Act: -0.1700
Data Index: 4394850 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8857. Min Range: -5.8857
Max Act: 5.1982. Min Act: -0.1700
Data Index: 79140 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8857. Min Range: -5.8857
Max Act: 5.1982. Min Act: -0.1700
Data Index: 908052 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #19