Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2817 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8492. Min Range: -8.8492
Max Act: 8.8492. Min Act: -0.1700
Data Index: 5434265 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8492. Min Range: -8.8492
Max Act: 8.7242. Min Act: -0.1700
Data Index: 2583052 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8492. Min Range: -8.8492
Max Act: 8.7242. Min Act: -0.1700
Data Index: 8528955 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8492. Min Range: -8.8492
Max Act: 8.6617. Min Act: -0.1700
Data Index: 8052670 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8492. Min Range: -8.8492
Max Act: 8.5992. Min Act: -0.1700
Data Index: 4601942 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8492. Min Range: -8.8492
Max Act: 8.5992. Min Act: -0.1700
Data Index: 2767168 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8492. Min Range: -8.8492
Max Act: 8.5992. Min Act: -0.1700
Data Index: 6850794 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8492. Min Range: -8.8492
Max Act: 8.5367. Min Act: -0.1700
Data Index: 4245749 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8492. Min Range: -8.8492
Max Act: 8.5367. Min Act: -0.1700
Data Index: 3045607 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8492. Min Range: -8.8492
Max Act: 8.5367. Min Act: -0.1700
Data Index: 7273885 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8492. Min Range: -8.8492
Max Act: 8.4742. Min Act: -0.1700
Data Index: 5409071 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8492. Min Range: -8.8492
Max Act: 8.4742. Min Act: -0.1700
Data Index: 3535139 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8492. Min Range: -8.8492
Max Act: 8.4117. Min Act: -0.1700
Data Index: 8105610 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8492. Min Range: -8.8492
Max Act: 8.4742. Min Act: -0.1700
Data Index: 3694179 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8492. Min Range: -8.8492
Max Act: 8.4117. Min Act: -0.1700
Data Index: 8090184 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8492. Min Range: -8.8492
Max Act: 8.3492. Min Act: -0.1700
Data Index: 2881138 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8492. Min Range: -8.8492
Max Act: 8.3492. Min Act: -0.1700
Data Index: 6865654 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8492. Min Range: -8.8492
Max Act: 8.3492. Min Act: -0.1700
Data Index: 2254743 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8492. Min Range: -8.8492
Max Act: 8.2867. Min Act: -0.1700
Data Index: 4976033 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8492. Min Range: -8.8492
Max Act: 8.2867. Min Act: -0.1700
Data Index: 1930201 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #19