Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5068 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7886. Min Range: -4.7886
Max Act: 4.7886. Min Act: -0.1700
Data Index: 6261818 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7886. Min Range: -4.7886
Max Act: 4.6324. Min Act: -0.1700
Data Index: 5737710 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7886. Min Range: -4.7886
Max Act: 4.6011. Min Act: -0.1700
Data Index: 5106907 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7886. Min Range: -4.7886
Max Act: 4.6011. Min Act: -0.1700
Data Index: 8098675 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7886. Min Range: -4.7886
Max Act: 4.6011. Min Act: -0.1700
Data Index: 1624064 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7886. Min Range: -4.7886
Max Act: 4.6011. Min Act: -0.1700
Data Index: 4019314 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7886. Min Range: -4.7886
Max Act: 4.4136. Min Act: -0.1700
Data Index: 1789759 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7886. Min Range: -4.7886
Max Act: 4.4136. Min Act: -0.1700
Data Index: 8785267 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7886. Min Range: -4.7886
Max Act: 4.3824. Min Act: -0.1700
Data Index: 207415 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7886. Min Range: -4.7886
Max Act: 4.3824. Min Act: -0.1700
Data Index: 5548971 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7886. Min Range: -4.7886
Max Act: 4.3511. Min Act: -0.1700
Data Index: 4563503 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7886. Min Range: -4.7886
Max Act: 4.3199. Min Act: -0.1700
Data Index: 8428796 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7886. Min Range: -4.7886
Max Act: 4.2886. Min Act: -0.1700
Data Index: 5082882 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7886. Min Range: -4.7886
Max Act: 4.2573. Min Act: -0.1700
Data Index: 891880 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7886. Min Range: -4.7886
Max Act: 4.2573. Min Act: -0.1700
Data Index: 7869354 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7886. Min Range: -4.7886
Max Act: 4.2261. Min Act: -0.1700
Data Index: 3831006 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7886. Min Range: -4.7886
Max Act: 4.1636. Min Act: -0.1700
Data Index: 2967756 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7886. Min Range: -4.7886
Max Act: 4.1948. Min Act: -0.1700
Data Index: 2140264 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7886. Min Range: -4.7886
Max Act: 4.1636. Min Act: -0.1700
Data Index: 8416930 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7886. Min Range: -4.7886
Max Act: 4.1323. Min Act: -0.1700
Data Index: 5005679 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #19