Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4480 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3650. Min Range: -5.3650
Max Act: 5.3650. Min Act: -0.1700
Data Index: 5532078 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3650. Min Range: -5.3650
Max Act: 5.2713. Min Act: -0.1700
Data Index: 7805963 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3650. Min Range: -5.3650
Max Act: 5.2400. Min Act: -0.1700
Data Index: 2910278 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3650. Min Range: -5.3650
Max Act: 5.2088. Min Act: -0.1700
Data Index: 7068416 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3650. Min Range: -5.3650
Max Act: 5.1775. Min Act: -0.1700
Data Index: 2910277 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3650. Min Range: -5.3650
Max Act: 5.1463. Min Act: -0.1700
Data Index: 2910279 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3650. Min Range: -5.3650
Max Act: 5.1463. Min Act: -0.1700
Data Index: 2910251 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3650. Min Range: -5.3650
Max Act: 5.1150. Min Act: -0.1700
Data Index: 5046288 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3650. Min Range: -5.3650
Max Act: 5.1150. Min Act: -0.1700
Data Index: 2636866 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3650. Min Range: -5.3650
Max Act: 5.0838. Min Act: -0.1700
Data Index: 2910273 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3650. Min Range: -5.3650
Max Act: 5.0838. Min Act: -0.1700
Data Index: 1537829 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3650. Min Range: -5.3650
Max Act: 5.0838. Min Act: -0.1700
Data Index: 7055119 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3650. Min Range: -5.3650
Max Act: 5.0838. Min Act: -0.1700
Data Index: 2479419 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3650. Min Range: -5.3650
Max Act: 5.0838. Min Act: -0.1700
Data Index: 5672165 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3650. Min Range: -5.3650
Max Act: 5.0525. Min Act: -0.1700
Data Index: 8046968 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3650. Min Range: -5.3650
Max Act: 5.0838. Min Act: -0.1700
Data Index: 3897233 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3650. Min Range: -5.3650
Max Act: 5.0213. Min Act: -0.1700
Data Index: 7623233 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3650. Min Range: -5.3650
Max Act: 5.0525. Min Act: -0.1700
Data Index: 8327915 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3650. Min Range: -5.3650
Max Act: 5.0525. Min Act: -0.1700
Data Index: 4811835 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3650. Min Range: -5.3650
Max Act: 5.0525. Min Act: -0.1700
Data Index: 2910274 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #19