Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3102 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 16.1034. Min Range: -16.1034
Max Act: 16.1034. Min Act: -0.1700
Data Index: 7930662 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 16.1034. Min Range: -16.1034
Max Act: 15.6659. Min Act: -0.1700
Data Index: 4004685 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 16.1034. Min Range: -16.1034
Max Act: 15.2909. Min Act: -0.1700
Data Index: 2264800 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 16.1034. Min Range: -16.1034
Max Act: 15.2284. Min Act: -0.1700
Data Index: 4659049 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 16.1034. Min Range: -16.1034
Max Act: 15.2284. Min Act: -0.1700
Data Index: 2390967 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 16.1034. Min Range: -16.1034
Max Act: 15.1659. Min Act: -0.1700
Data Index: 5499041 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 16.1034. Min Range: -16.1034
Max Act: 15.1659. Min Act: -0.1700
Data Index: 4343843 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 16.1034. Min Range: -16.1034
Max Act: 15.1034. Min Act: -0.1700
Data Index: 4325799 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 16.1034. Min Range: -16.1034
Max Act: 15.0409. Min Act: -0.1700
Data Index: 5181144 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 16.1034. Min Range: -16.1034
Max Act: 15.0409. Min Act: -0.1700
Data Index: 2705442 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 16.1034. Min Range: -16.1034
Max Act: 15.0409. Min Act: -0.1700
Data Index: 2052931 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 16.1034. Min Range: -16.1034
Max Act: 14.9159. Min Act: -0.1700
Data Index: 3937801 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 16.1034. Min Range: -16.1034
Max Act: 14.9159. Min Act: -0.1700
Data Index: 6041254 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 16.1034. Min Range: -16.1034
Max Act: 14.8534. Min Act: -0.1700
Data Index: 462587 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 16.1034. Min Range: -16.1034
Max Act: 14.9159. Min Act: -0.1700
Data Index: 6793833 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 16.1034. Min Range: -16.1034
Max Act: 14.8534. Min Act: -0.1700
Data Index: 1407250 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 16.1034. Min Range: -16.1034
Max Act: 14.7909. Min Act: -0.1700
Data Index: 5580369 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 16.1034. Min Range: -16.1034
Max Act: 14.7909. Min Act: -0.1700
Data Index: 2373819 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 16.1034. Min Range: -16.1034
Max Act: 14.7284. Min Act: -0.1700
Data Index: 3506206 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 16.1034. Min Range: -16.1034
Max Act: 14.7284. Min Act: -0.1700
Data Index: 5916651 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #19