Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3888 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.8199. Min Range: -2.8199
Max Act: 2.8199. Min Act: -0.1700
Data Index: 2719689 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8199. Min Range: -2.8199
Max Act: 2.7242. Min Act: -0.1700
Data Index: 2232081 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8199. Min Range: -2.8199
Max Act: 2.7402. Min Act: -0.1700
Data Index: 1573424 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8199. Min Range: -2.8199
Max Act: 2.7402. Min Act: -0.1700
Data Index: 4833141 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8199. Min Range: -2.8199
Max Act: 2.7082. Min Act: -0.1700
Data Index: 4958705 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8199. Min Range: -2.8199
Max Act: 2.6922. Min Act: -0.1700
Data Index: 5270720 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8199. Min Range: -2.8199
Max Act: 2.6762. Min Act: -0.1700
Data Index: 1284789 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8199. Min Range: -2.8199
Max Act: 2.6762. Min Act: -0.1700
Data Index: 2501922 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8199. Min Range: -2.8199
Max Act: 2.6441. Min Act: -0.1700
Data Index: 2011988 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8199. Min Range: -2.8199
Max Act: 2.6441. Min Act: -0.1700
Data Index: 4861924 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8199. Min Range: -2.8199
Max Act: 2.6281. Min Act: -0.1700
Data Index: 5059688 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8199. Min Range: -2.8199
Max Act: 2.6281. Min Act: -0.1700
Data Index: 5551094 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8199. Min Range: -2.8199
Max Act: 2.6281. Min Act: -0.1700
Data Index: 131090 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8199. Min Range: -2.8199
Max Act: 2.6120. Min Act: -0.1700
Data Index: 3250923 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8199. Min Range: -2.8199
Max Act: 2.6120. Min Act: -0.1700
Data Index: 40911 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8199. Min Range: -2.8199
Max Act: 2.6120. Min Act: -0.1700
Data Index: 8018952 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8199. Min Range: -2.8199
Max Act: 2.6120. Min Act: -0.1700
Data Index: 5579810 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8199. Min Range: -2.8199
Max Act: 2.6120. Min Act: -0.1700
Data Index: 546581 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8199. Min Range: -2.8199
Max Act: 2.6120. Min Act: -0.1700
Data Index: 6682860 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8199. Min Range: -2.8199
Max Act: 2.6120. Min Act: -0.1700
Data Index: 334612 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #19