Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4974 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.3948. Min Range: -5.3948
Max Act: 5.3948. Min Act: -0.1700
Data Index: 345557 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3948. Min Range: -5.3948
Max Act: 5.2698. Min Act: -0.1700
Data Index: 6262941 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3948. Min Range: -5.3948
Max Act: 5.2698. Min Act: -0.1700
Data Index: 4571543 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3948. Min Range: -5.3948
Max Act: 5.2073. Min Act: -0.1700
Data Index: 726097 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3948. Min Range: -5.3948
Max Act: 5.2385. Min Act: -0.1700
Data Index: 1064025 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3948. Min Range: -5.3948
Max Act: 5.2385. Min Act: -0.1700
Data Index: 6800205 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3948. Min Range: -5.3948
Max Act: 5.1760. Min Act: -0.1700
Data Index: 7547507 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3948. Min Range: -5.3948
Max Act: 5.1760. Min Act: -0.1700
Data Index: 2924526 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3948. Min Range: -5.3948
Max Act: 5.1760. Min Act: -0.1700
Data Index: 139655 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3948. Min Range: -5.3948
Max Act: 5.1760. Min Act: -0.1700
Data Index: 2556876 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3948. Min Range: -5.3948
Max Act: 5.1760. Min Act: -0.1700
Data Index: 8161204 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3948. Min Range: -5.3948
Max Act: 5.1448. Min Act: -0.1700
Data Index: 341112 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3948. Min Range: -5.3948
Max Act: 5.0823. Min Act: -0.1700
Data Index: 820166 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3948. Min Range: -5.3948
Max Act: 5.0823. Min Act: -0.1700
Data Index: 817314 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3948. Min Range: -5.3948
Max Act: 5.1135. Min Act: -0.1700
Data Index: 5712827 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3948. Min Range: -5.3948
Max Act: 5.0823. Min Act: -0.1700
Data Index: 3784986 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3948. Min Range: -5.3948
Max Act: 5.1135. Min Act: -0.1700
Data Index: 2880776 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3948. Min Range: -5.3948
Max Act: 5.0823. Min Act: -0.1700
Data Index: 8481590 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3948. Min Range: -5.3948
Max Act: 5.0823. Min Act: -0.1700
Data Index: 7148736 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3948. Min Range: -5.3948
Max Act: 5.0823. Min Act: -0.1700
Data Index: 5449525 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #19