Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5757 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7708. Min Range: -7.7708
Max Act: 7.7708. Min Act: -0.1700
Data Index: 2173669 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7708. Min Range: -7.7708
Max Act: 7.6770. Min Act: -0.1700
Data Index: 6840031 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7708. Min Range: -7.7708
Max Act: 7.6145. Min Act: -0.1700
Data Index: 1283814 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7708. Min Range: -7.7708
Max Act: 7.5833. Min Act: -0.1700
Data Index: 5062113 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7708. Min Range: -7.7708
Max Act: 7.5208. Min Act: -0.1700
Data Index: 1882401 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7708. Min Range: -7.7708
Max Act: 7.4895. Min Act: -0.1700
Data Index: 2270120 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7708. Min Range: -7.7708
Max Act: 7.4270. Min Act: -0.1700
Data Index: 912308 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7708. Min Range: -7.7708
Max Act: 7.3645. Min Act: -0.1700
Data Index: 6561692 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7708. Min Range: -7.7708
Max Act: 7.3645. Min Act: -0.1700
Data Index: 3004002 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7708. Min Range: -7.7708
Max Act: 7.3645. Min Act: -0.1700
Data Index: 5191273 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7708. Min Range: -7.7708
Max Act: 7.3645. Min Act: -0.1700
Data Index: 8478685 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7708. Min Range: -7.7708
Max Act: 7.3333. Min Act: -0.1700
Data Index: 5661237 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7708. Min Range: -7.7708
Max Act: 7.3333. Min Act: -0.1700
Data Index: 3768873 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7708. Min Range: -7.7708
Max Act: 7.2708. Min Act: -0.1700
Data Index: 532907 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7708. Min Range: -7.7708
Max Act: 7.3020. Min Act: -0.1700
Data Index: 3351610 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7708. Min Range: -7.7708
Max Act: 7.3020. Min Act: -0.1700
Data Index: 4802673 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7708. Min Range: -7.7708
Max Act: 7.2708. Min Act: -0.1700
Data Index: 308220 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7708. Min Range: -7.7708
Max Act: 7.2708. Min Act: -0.1700
Data Index: 6214610 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7708. Min Range: -7.7708
Max Act: 7.2395. Min Act: -0.1700
Data Index: 617796 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7708. Min Range: -7.7708
Max Act: 7.2083. Min Act: -0.1700
Data Index: 3148650 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #19