Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3927 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6664. Min Range: -5.6664
Max Act: 5.6664. Min Act: -0.1700
Data Index: 7041100 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6664. Min Range: -5.6664
Max Act: 5.6351. Min Act: -0.1700
Data Index: 5689067 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6664. Min Range: -5.6664
Max Act: 5.5414. Min Act: -0.1700
Data Index: 1730429 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6664. Min Range: -5.6664
Max Act: 5.5101. Min Act: -0.1700
Data Index: 2352860 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6664. Min Range: -5.6664
Max Act: 5.3851. Min Act: -0.1700
Data Index: 1966642 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6664. Min Range: -5.6664
Max Act: 5.3539. Min Act: -0.1700
Data Index: 1576467 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6664. Min Range: -5.6664
Max Act: 5.3851. Min Act: -0.1700
Data Index: 3964392 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6664. Min Range: -5.6664
Max Act: 5.3851. Min Act: -0.1700
Data Index: 7538143 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6664. Min Range: -5.6664
Max Act: 5.3851. Min Act: -0.1700
Data Index: 5029404 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6664. Min Range: -5.6664
Max Act: 5.3539. Min Act: -0.1700
Data Index: 8471811 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6664. Min Range: -5.6664
Max Act: 5.3226. Min Act: -0.1700
Data Index: 397606 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6664. Min Range: -5.6664
Max Act: 5.2914. Min Act: -0.1700
Data Index: 3122473 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6664. Min Range: -5.6664
Max Act: 5.2601. Min Act: -0.1700
Data Index: 1138484 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6664. Min Range: -5.6664
Max Act: 5.2601. Min Act: -0.1700
Data Index: 7651307 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6664. Min Range: -5.6664
Max Act: 5.2601. Min Act: -0.1700
Data Index: 8346281 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6664. Min Range: -5.6664
Max Act: 5.2289. Min Act: -0.1700
Data Index: 786066 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6664. Min Range: -5.6664
Max Act: 5.2289. Min Act: -0.1700
Data Index: 4524504 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6664. Min Range: -5.6664
Max Act: 5.2289. Min Act: -0.1700
Data Index: 6918403 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6664. Min Range: -5.6664
Max Act: 5.1976. Min Act: -0.1700
Data Index: 7719090 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6664. Min Range: -5.6664
Max Act: 5.1976. Min Act: -0.1700
Data Index: 4790198 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #19