Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5466 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8120. Min Range: -5.8120
Max Act: 5.8120. Min Act: -0.1700
Data Index: 2101827 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8120. Min Range: -5.8120
Max Act: 5.8120. Min Act: -0.1700
Data Index: 1573868 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8120. Min Range: -5.8120
Max Act: 5.7808. Min Act: -0.1700
Data Index: 6181454 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8120. Min Range: -5.8120
Max Act: 5.7495. Min Act: -0.1700
Data Index: 53566 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8120. Min Range: -5.8120
Max Act: 5.7183. Min Act: -0.1700
Data Index: 2019439 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8120. Min Range: -5.8120
Max Act: 5.6870. Min Act: -0.1700
Data Index: 5508914 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8120. Min Range: -5.8120
Max Act: 5.7183. Min Act: -0.1700
Data Index: 2390290 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8120. Min Range: -5.8120
Max Act: 5.6870. Min Act: -0.1700
Data Index: 6773187 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8120. Min Range: -5.8120
Max Act: 5.6558. Min Act: -0.1700
Data Index: 3949154 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8120. Min Range: -5.8120
Max Act: 5.6558. Min Act: -0.1700
Data Index: 616080 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8120. Min Range: -5.8120
Max Act: 5.6558. Min Act: -0.1700
Data Index: 7483245 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8120. Min Range: -5.8120
Max Act: 5.6245. Min Act: -0.1700
Data Index: 6317423 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8120. Min Range: -5.8120
Max Act: 5.6245. Min Act: -0.1700
Data Index: 5908380 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8120. Min Range: -5.8120
Max Act: 5.6558. Min Act: -0.1700
Data Index: 5604926 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8120. Min Range: -5.8120
Max Act: 5.6245. Min Act: -0.1700
Data Index: 3482143 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8120. Min Range: -5.8120
Max Act: 5.6245. Min Act: -0.1700
Data Index: 4103858 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8120. Min Range: -5.8120
Max Act: 5.5620. Min Act: -0.1700
Data Index: 352999 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8120. Min Range: -5.8120
Max Act: 5.5933. Min Act: -0.1700
Data Index: 5336899 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8120. Min Range: -5.8120
Max Act: 5.5620. Min Act: -0.1700
Data Index: 1363734 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8120. Min Range: -5.8120
Max Act: 5.5933. Min Act: -0.1700
Data Index: 7558135 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #19