Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3571 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7536. Min Range: -7.7536
Max Act: 7.7536. Min Act: -0.1700
Data Index: 2550448 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7536. Min Range: -7.7536
Max Act: 7.7536. Min Act: -0.1700
Data Index: 3619815 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7536. Min Range: -7.7536
Max Act: 7.4724. Min Act: -0.1700
Data Index: 5775414 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7536. Min Range: -7.7536
Max Act: 7.4724. Min Act: -0.1700
Data Index: 7596951 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7536. Min Range: -7.7536
Max Act: 7.4411. Min Act: -0.1700
Data Index: 901336 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7536. Min Range: -7.7536
Max Act: 7.4099. Min Act: -0.1700
Data Index: 4025693 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7536. Min Range: -7.7536
Max Act: 7.4099. Min Act: -0.1700
Data Index: 1303912 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7536. Min Range: -7.7536
Max Act: 7.3786. Min Act: -0.1700
Data Index: 1840542 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7536. Min Range: -7.7536
Max Act: 7.3474. Min Act: -0.1700
Data Index: 1108468 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7536. Min Range: -7.7536
Max Act: 7.3474. Min Act: -0.1700
Data Index: 3984735 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7536. Min Range: -7.7536
Max Act: 7.3161. Min Act: -0.1700
Data Index: 883973 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7536. Min Range: -7.7536
Max Act: 7.2849. Min Act: -0.1700
Data Index: 938050 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7536. Min Range: -7.7536
Max Act: 7.2849. Min Act: -0.1700
Data Index: 6990242 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7536. Min Range: -7.7536
Max Act: 7.2849. Min Act: -0.1700
Data Index: 913035 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7536. Min Range: -7.7536
Max Act: 7.2849. Min Act: -0.1700
Data Index: 938052 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7536. Min Range: -7.7536
Max Act: 7.2536. Min Act: -0.1700
Data Index: 4075511 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7536. Min Range: -7.7536
Max Act: 7.2536. Min Act: -0.1700
Data Index: 4243915 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7536. Min Range: -7.7536
Max Act: 7.2536. Min Act: -0.1700
Data Index: 1596472 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7536. Min Range: -7.7536
Max Act: 7.2536. Min Act: -0.1700
Data Index: 7198962 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7536. Min Range: -7.7536
Max Act: 7.2224. Min Act: -0.1700
Data Index: 7329858 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #19