Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2286 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.3115. Min Range: -2.3115
Max Act: 2.3115. Min Act: -0.1700
Data Index: 5447543 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3115. Min Range: -2.3115
Max Act: 2.2951. Min Act: -0.1700
Data Index: 8589252 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3115. Min Range: -2.3115
Max Act: 2.2291. Min Act: -0.1700
Data Index: 1082058 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3115. Min Range: -2.3115
Max Act: 2.2125. Min Act: -0.1700
Data Index: 752571 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3115. Min Range: -2.3115
Max Act: 2.2125. Min Act: -0.1700
Data Index: 4589430 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3115. Min Range: -2.3115
Max Act: 2.1959. Min Act: -0.1698
Data Index: 6894495 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3115. Min Range: -2.3115
Max Act: 2.1793. Min Act: -0.1700
Data Index: 6752241 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3115. Min Range: -2.3115
Max Act: 2.1627. Min Act: -0.1700
Data Index: 3215099 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3115. Min Range: -2.3115
Max Act: 2.1627. Min Act: -0.1699
Data Index: 7179609 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3115. Min Range: -2.3115
Max Act: 2.1627. Min Act: -0.1700
Data Index: 4689265 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3115. Min Range: -2.3115
Max Act: 2.1460. Min Act: -0.1700
Data Index: 981970 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3115. Min Range: -2.3115
Max Act: 2.1293. Min Act: -0.1700
Data Index: 5667206 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3115. Min Range: -2.3115
Max Act: 2.1293. Min Act: -0.1700
Data Index: 3087911 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3115. Min Range: -2.3115
Max Act: 2.1293. Min Act: -0.1700
Data Index: 178677 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3115. Min Range: -2.3115
Max Act: 2.1293. Min Act: -0.1700
Data Index: 4812298 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3115. Min Range: -2.3115
Max Act: 2.1293. Min Act: -0.1700
Data Index: 1736552 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3115. Min Range: -2.3115
Max Act: 2.1293. Min Act: -0.1700
Data Index: 4351222 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3115. Min Range: -2.3115
Max Act: 2.1126. Min Act: -0.1700
Data Index: 3950321 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3115. Min Range: -2.3115
Max Act: 2.1126. Min Act: -0.1700
Data Index: 4014203 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3115. Min Range: -2.3115
Max Act: 2.1126. Min Act: -0.1700
Data Index: 6223008 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #19