Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5127 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5422. Min Range: -7.5422
Max Act: 7.5422. Min Act: -0.1700
Data Index: 5502781 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5422. Min Range: -7.5422
Max Act: 7.2610. Min Act: -0.1700
Data Index: 2358298 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5422. Min Range: -7.5422
Max Act: 7.1360. Min Act: -0.1700
Data Index: 6975750 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5422. Min Range: -7.5422
Max Act: 7.0735. Min Act: -0.1700
Data Index: 3897653 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5422. Min Range: -7.5422
Max Act: 6.9797. Min Act: -0.1700
Data Index: 5068204 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5422. Min Range: -7.5422
Max Act: 6.8235. Min Act: -0.1700
Data Index: 5517958 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5422. Min Range: -7.5422
Max Act: 6.8547. Min Act: -0.1700
Data Index: 5799345 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5422. Min Range: -7.5422
Max Act: 6.7922. Min Act: -0.1700
Data Index: 7899818 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5422. Min Range: -7.5422
Max Act: 6.7297. Min Act: -0.1700
Data Index: 7566737 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5422. Min Range: -7.5422
Max Act: 6.6985. Min Act: -0.1700
Data Index: 5470729 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5422. Min Range: -7.5422
Max Act: 6.6672. Min Act: -0.1700
Data Index: 3038603 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5422. Min Range: -7.5422
Max Act: 6.6360. Min Act: -0.1700
Data Index: 4649383 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5422. Min Range: -7.5422
Max Act: 6.6672. Min Act: -0.1700
Data Index: 3733793 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5422. Min Range: -7.5422
Max Act: 6.6360. Min Act: -0.1700
Data Index: 3318297 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5422. Min Range: -7.5422
Max Act: 6.6360. Min Act: -0.1700
Data Index: 3967862 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5422. Min Range: -7.5422
Max Act: 6.5735. Min Act: -0.1700
Data Index: 6212760 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5422. Min Range: -7.5422
Max Act: 6.5735. Min Act: -0.1700
Data Index: 1456076 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5422. Min Range: -7.5422
Max Act: 6.5422. Min Act: -0.1700
Data Index: 6589920 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5422. Min Range: -7.5422
Max Act: 6.5110. Min Act: -0.1700
Data Index: 5508612 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5422. Min Range: -7.5422
Max Act: 6.5422. Min Act: -0.1700
Data Index: 6630040 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #19