Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4530 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5635. Min Range: -5.5635
Max Act: 5.5635. Min Act: -0.1700
Data Index: 3547414 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5635. Min Range: -5.5635
Max Act: 5.4697. Min Act: -0.1700
Data Index: 3032323 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5635. Min Range: -5.5635
Max Act: 5.4385. Min Act: -0.1700
Data Index: 1767992 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5635. Min Range: -5.5635
Max Act: 5.4385. Min Act: -0.1700
Data Index: 1944838 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5635. Min Range: -5.5635
Max Act: 5.4072. Min Act: -0.1700
Data Index: 8202770 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5635. Min Range: -5.5635
Max Act: 5.3760. Min Act: -0.1700
Data Index: 2547983 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5635. Min Range: -5.5635
Max Act: 5.3447. Min Act: -0.1700
Data Index: 6601275 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5635. Min Range: -5.5635
Max Act: 5.3135. Min Act: -0.1700
Data Index: 901149 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5635. Min Range: -5.5635
Max Act: 5.3135. Min Act: -0.1700
Data Index: 6030248 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5635. Min Range: -5.5635
Max Act: 5.3135. Min Act: -0.1700
Data Index: 3420156 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5635. Min Range: -5.5635
Max Act: 5.2822. Min Act: -0.1700
Data Index: 7951651 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5635. Min Range: -5.5635
Max Act: 5.2510. Min Act: -0.1700
Data Index: 2983472 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5635. Min Range: -5.5635
Max Act: 5.2510. Min Act: -0.1700
Data Index: 7421035 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5635. Min Range: -5.5635
Max Act: 5.2510. Min Act: -0.1700
Data Index: 524880 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5635. Min Range: -5.5635
Max Act: 5.2197. Min Act: -0.1700
Data Index: 2571017 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5635. Min Range: -5.5635
Max Act: 5.2197. Min Act: -0.1700
Data Index: 2502931 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5635. Min Range: -5.5635
Max Act: 5.2197. Min Act: -0.1700
Data Index: 4816856 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5635. Min Range: -5.5635
Max Act: 5.2197. Min Act: -0.1700
Data Index: 3854561 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5635. Min Range: -5.5635
Max Act: 5.2197. Min Act: -0.1700
Data Index: 2359415 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5635. Min Range: -5.5635
Max Act: 5.2197. Min Act: -0.1700
Data Index: 6089216 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #19