Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1782 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5392. Min Range: -3.5392
Max Act: 3.5392. Min Act: -0.1700
Data Index: 2288571 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5392. Min Range: -3.5392
Max Act: 3.5079. Min Act: -0.1700
Data Index: 2077107 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5392. Min Range: -3.5392
Max Act: 3.4765. Min Act: -0.1700
Data Index: 6553551 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5392. Min Range: -3.5392
Max Act: 3.4609. Min Act: -0.1700
Data Index: 4129999 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5392. Min Range: -3.5392
Max Act: 3.4452. Min Act: -0.1700
Data Index: 5025696 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5392. Min Range: -3.5392
Max Act: 3.4295. Min Act: -0.1700
Data Index: 2759820 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5392. Min Range: -3.5392
Max Act: 3.4138. Min Act: -0.1700
Data Index: 1581090 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5392. Min Range: -3.5392
Max Act: 3.4138. Min Act: -0.1700
Data Index: 2336819 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5392. Min Range: -3.5392
Max Act: 3.4138. Min Act: -0.1700
Data Index: 2964824 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5392. Min Range: -3.5392
Max Act: 3.4138. Min Act: -0.1700
Data Index: 121977 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5392. Min Range: -3.5392
Max Act: 3.3982. Min Act: -0.1700
Data Index: 8206856 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5392. Min Range: -3.5392
Max Act: 3.3982. Min Act: -0.1700
Data Index: 983107 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5392. Min Range: -3.5392
Max Act: 3.3668. Min Act: -0.1700
Data Index: 5621912 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5392. Min Range: -3.5392
Max Act: 3.3825. Min Act: -0.1700
Data Index: 6469475 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5392. Min Range: -3.5392
Max Act: 3.3668. Min Act: -0.1700
Data Index: 894383 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5392. Min Range: -3.5392
Max Act: 3.3197. Min Act: -0.1700
Data Index: 597842 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5392. Min Range: -3.5392
Max Act: 3.3197. Min Act: -0.1700
Data Index: 6255028 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5392. Min Range: -3.5392
Max Act: 3.2883. Min Act: -0.1700
Data Index: 8256324 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5392. Min Range: -3.5392
Max Act: 3.3040. Min Act: -0.1700
Data Index: 4310814 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5392. Min Range: -3.5392
Max Act: 3.3040. Min Act: -0.1700
Data Index: 7107101 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #19