Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1945 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2115. Min Range: -7.2115
Max Act: 7.2115. Min Act: -0.1700
Data Index: 6317886 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2115. Min Range: -7.2115
Max Act: 7.1178. Min Act: -0.1700
Data Index: 2818991 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2115. Min Range: -7.2115
Max Act: 6.9615. Min Act: -0.1700
Data Index: 4460749 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2115. Min Range: -7.2115
Max Act: 6.8365. Min Act: -0.1700
Data Index: 5967089 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2115. Min Range: -7.2115
Max Act: 6.7428. Min Act: -0.1700
Data Index: 2636269 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2115. Min Range: -7.2115
Max Act: 6.6490. Min Act: -0.1700
Data Index: 150435 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2115. Min Range: -7.2115
Max Act: 6.6490. Min Act: -0.1700
Data Index: 663689 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2115. Min Range: -7.2115
Max Act: 6.6178. Min Act: -0.1700
Data Index: 712610 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2115. Min Range: -7.2115
Max Act: 6.5865. Min Act: -0.1700
Data Index: 7415566 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2115. Min Range: -7.2115
Max Act: 6.6178. Min Act: -0.1700
Data Index: 4927271 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2115. Min Range: -7.2115
Max Act: 6.5553. Min Act: -0.1700
Data Index: 6703869 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2115. Min Range: -7.2115
Max Act: 6.5553. Min Act: -0.1700
Data Index: 1930262 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2115. Min Range: -7.2115
Max Act: 6.5553. Min Act: -0.1700
Data Index: 6361789 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2115. Min Range: -7.2115
Max Act: 6.5240. Min Act: -0.1700
Data Index: 5424905 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2115. Min Range: -7.2115
Max Act: 6.5240. Min Act: -0.1700
Data Index: 6521074 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2115. Min Range: -7.2115
Max Act: 6.5240. Min Act: -0.1700
Data Index: 7938731 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2115. Min Range: -7.2115
Max Act: 6.5240. Min Act: -0.1700
Data Index: 1588997 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2115. Min Range: -7.2115
Max Act: 6.4928. Min Act: -0.1700
Data Index: 8803379 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2115. Min Range: -7.2115
Max Act: 6.4303. Min Act: -0.1700
Data Index: 4864682 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2115. Min Range: -7.2115
Max Act: 6.4303. Min Act: -0.1700
Data Index: 5155237 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #19