Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3720 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4859. Min Range: -5.4859
Max Act: 5.4859. Min Act: -0.1700
Data Index: 4737033 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4859. Min Range: -5.4859
Max Act: 5.4547. Min Act: -0.1700
Data Index: 4245970 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4859. Min Range: -5.4859
Max Act: 5.3922. Min Act: -0.1700
Data Index: 2008467 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4859. Min Range: -5.4859
Max Act: 5.3609. Min Act: -0.1700
Data Index: 707964 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4859. Min Range: -5.4859
Max Act: 5.3609. Min Act: -0.1700
Data Index: 1565675 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4859. Min Range: -5.4859
Max Act: 5.3609. Min Act: -0.1700
Data Index: 3485399 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4859. Min Range: -5.4859
Max Act: 5.3297. Min Act: -0.1700
Data Index: 7743763 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4859. Min Range: -5.4859
Max Act: 5.3297. Min Act: -0.1700
Data Index: 3222721 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4859. Min Range: -5.4859
Max Act: 5.3609. Min Act: -0.1700
Data Index: 4153420 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4859. Min Range: -5.4859
Max Act: 5.3297. Min Act: -0.1700
Data Index: 6729401 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4859. Min Range: -5.4859
Max Act: 5.2984. Min Act: -0.1700
Data Index: 6921853 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4859. Min Range: -5.4859
Max Act: 5.2984. Min Act: -0.1700
Data Index: 6952270 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4859. Min Range: -5.4859
Max Act: 5.2984. Min Act: -0.1700
Data Index: 7159889 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4859. Min Range: -5.4859
Max Act: 5.2984. Min Act: -0.1700
Data Index: 8529671 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4859. Min Range: -5.4859
Max Act: 5.2672. Min Act: -0.1700
Data Index: 4353596 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4859. Min Range: -5.4859
Max Act: 5.2672. Min Act: -0.1700
Data Index: 887035 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4859. Min Range: -5.4859
Max Act: 5.2672. Min Act: -0.1700
Data Index: 6782229 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4859. Min Range: -5.4859
Max Act: 5.2672. Min Act: -0.1700
Data Index: 3459591 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4859. Min Range: -5.4859
Max Act: 5.2672. Min Act: -0.1700
Data Index: 767312 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4859. Min Range: -5.4859
Max Act: 5.2359. Min Act: -0.1700
Data Index: 5457790 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #19