Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4795 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7003. Min Range: -5.7003
Max Act: 5.7003. Min Act: -0.1700
Data Index: 2513979 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7003. Min Range: -5.7003
Max Act: 5.6065. Min Act: -0.1700
Data Index: 7740920 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7003. Min Range: -5.7003
Max Act: 5.5440. Min Act: -0.1700
Data Index: 5503230 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7003. Min Range: -5.7003
Max Act: 5.5440. Min Act: -0.1700
Data Index: 2310046 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7003. Min Range: -5.7003
Max Act: 5.5440. Min Act: -0.1700
Data Index: 747524 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7003. Min Range: -5.7003
Max Act: 5.4815. Min Act: -0.1700
Data Index: 4758532 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7003. Min Range: -5.7003
Max Act: 5.4503. Min Act: -0.1700
Data Index: 7299732 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7003. Min Range: -5.7003
Max Act: 5.4503. Min Act: -0.1700
Data Index: 7838432 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7003. Min Range: -5.7003
Max Act: 5.4503. Min Act: -0.1700
Data Index: 6985204 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7003. Min Range: -5.7003
Max Act: 5.4503. Min Act: -0.1700
Data Index: 3672535 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7003. Min Range: -5.7003
Max Act: 5.4190. Min Act: -0.1700
Data Index: 3746578 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7003. Min Range: -5.7003
Max Act: 5.3878. Min Act: -0.1700
Data Index: 2070717 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7003. Min Range: -5.7003
Max Act: 5.3878. Min Act: -0.1700
Data Index: 2241549 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7003. Min Range: -5.7003
Max Act: 5.4190. Min Act: -0.1700
Data Index: 1110832 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7003. Min Range: -5.7003
Max Act: 5.3878. Min Act: -0.1698
Data Index: 2058450 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7003. Min Range: -5.7003
Max Act: 5.3565. Min Act: -0.1700
Data Index: 2438829 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7003. Min Range: -5.7003
Max Act: 5.3878. Min Act: -0.1700
Data Index: 3015258 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7003. Min Range: -5.7003
Max Act: 5.3878. Min Act: -0.1700
Data Index: 1775340 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7003. Min Range: -5.7003
Max Act: 5.3253. Min Act: -0.1700
Data Index: 4773703 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7003. Min Range: -5.7003
Max Act: 5.3253. Min Act: -0.1700
Data Index: 6438063 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #19