Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4906 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9274. Min Range: -5.9274
Max Act: 5.9274. Min Act: -0.1700
Data Index: 4882252 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9274. Min Range: -5.9274
Max Act: 5.7711. Min Act: -0.1700
Data Index: 2557207 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9274. Min Range: -5.9274
Max Act: 5.7399. Min Act: -0.1700
Data Index: 1370395 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9274. Min Range: -5.9274
Max Act: 5.7086. Min Act: -0.1700
Data Index: 1777851 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9274. Min Range: -5.9274
Max Act: 5.6774. Min Act: -0.1700
Data Index: 2136189 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9274. Min Range: -5.9274
Max Act: 5.6461. Min Act: -0.1700
Data Index: 8540396 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9274. Min Range: -5.9274
Max Act: 5.6461. Min Act: -0.1700
Data Index: 4435415 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9274. Min Range: -5.9274
Max Act: 5.6461. Min Act: -0.1700
Data Index: 4556835 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9274. Min Range: -5.9274
Max Act: 5.6461. Min Act: -0.1700
Data Index: 6900591 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9274. Min Range: -5.9274
Max Act: 5.6149. Min Act: -0.1700
Data Index: 1174077 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9274. Min Range: -5.9274
Max Act: 5.6149. Min Act: -0.1700
Data Index: 8120083 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9274. Min Range: -5.9274
Max Act: 5.5524. Min Act: -0.1700
Data Index: 3373380 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9274. Min Range: -5.9274
Max Act: 5.5524. Min Act: -0.1700
Data Index: 2827774 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9274. Min Range: -5.9274
Max Act: 5.5524. Min Act: -0.1700
Data Index: 6591599 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9274. Min Range: -5.9274
Max Act: 5.5524. Min Act: -0.1700
Data Index: 776500 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9274. Min Range: -5.9274
Max Act: 5.5524. Min Act: -0.1700
Data Index: 105121 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9274. Min Range: -5.9274
Max Act: 5.5524. Min Act: -0.1700
Data Index: 228858 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9274. Min Range: -5.9274
Max Act: 5.5211. Min Act: -0.1700
Data Index: 3888750 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9274. Min Range: -5.9274
Max Act: 5.4899. Min Act: -0.1700
Data Index: 7163630 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9274. Min Range: -5.9274
Max Act: 5.5211. Min Act: -0.1700
Data Index: 2935476 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #19