Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 528 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3497. Min Range: -6.3497
Max Act: 6.3497. Min Act: -0.1700
Data Index: 8152889 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3497. Min Range: -6.3497
Max Act: 6.0685. Min Act: -0.1700
Data Index: 926935 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3497. Min Range: -6.3497
Max Act: 6.0060. Min Act: -0.1700
Data Index: 1106073 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3497. Min Range: -6.3497
Max Act: 6.0060. Min Act: -0.1700
Data Index: 7900034 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3497. Min Range: -6.3497
Max Act: 5.9747. Min Act: -0.1700
Data Index: 230501 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3497. Min Range: -6.3497
Max Act: 5.9747. Min Act: -0.1700
Data Index: 8693577 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3497. Min Range: -6.3497
Max Act: 5.9435. Min Act: -0.1700
Data Index: 7473953 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3497. Min Range: -6.3497
Max Act: 5.9435. Min Act: -0.1700
Data Index: 3648604 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3497. Min Range: -6.3497
Max Act: 5.9122. Min Act: -0.1700
Data Index: 5852629 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3497. Min Range: -6.3497
Max Act: 5.9122. Min Act: -0.1700
Data Index: 4478423 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3497. Min Range: -6.3497
Max Act: 5.8497. Min Act: -0.1700
Data Index: 280237 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3497. Min Range: -6.3497
Max Act: 5.8185. Min Act: -0.1700
Data Index: 810615 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3497. Min Range: -6.3497
Max Act: 5.7560. Min Act: -0.1700
Data Index: 3615643 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3497. Min Range: -6.3497
Max Act: 5.7560. Min Act: -0.1700
Data Index: 6571641 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3497. Min Range: -6.3497
Max Act: 5.7560. Min Act: -0.1700
Data Index: 2908871 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3497. Min Range: -6.3497
Max Act: 5.6935. Min Act: -0.1700
Data Index: 8786607 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3497. Min Range: -6.3497
Max Act: 5.6622. Min Act: -0.1700
Data Index: 4971571 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3497. Min Range: -6.3497
Max Act: 5.6310. Min Act: -0.1700
Data Index: 736763 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3497. Min Range: -6.3497
Max Act: 5.6310. Min Act: -0.1700
Data Index: 340306 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3497. Min Range: -6.3497
Max Act: 5.5997. Min Act: -0.1700
Data Index: 6554097 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #19