Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 855 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.0820. Min Range: -3.0820
Max Act: 3.0820. Min Act: -0.1700
Data Index: 62468 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0820. Min Range: -3.0820
Max Act: 3.0504. Min Act: -0.1700
Data Index: 1164526 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0820. Min Range: -3.0820
Max Act: 3.0189. Min Act: -0.1700
Data Index: 5344176 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0820. Min Range: -3.0820
Max Act: 3.0189. Min Act: -0.1700
Data Index: 5188784 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0820. Min Range: -3.0820
Max Act: 3.0031. Min Act: -0.1700
Data Index: 5951872 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0820. Min Range: -3.0820
Max Act: 3.0031. Min Act: -0.1700
Data Index: 4348668 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0820. Min Range: -3.0820
Max Act: 2.9715. Min Act: -0.1700
Data Index: 7193883 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0820. Min Range: -3.0820
Max Act: 2.9715. Min Act: -0.1700
Data Index: 528600 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0820. Min Range: -3.0820
Max Act: 2.9715. Min Act: -0.1700
Data Index: 8705164 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0820. Min Range: -3.0820
Max Act: 2.9715. Min Act: -0.1700
Data Index: 6879991 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0820. Min Range: -3.0820
Max Act: 2.9398. Min Act: -0.1700
Data Index: 767210 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0820. Min Range: -3.0820
Max Act: 2.9556. Min Act: -0.1700
Data Index: 7172457 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0820. Min Range: -3.0820
Max Act: 2.9556. Min Act: -0.1700
Data Index: 3567571 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0820. Min Range: -3.0820
Max Act: 2.9398. Min Act: -0.1700
Data Index: 1947674 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0820. Min Range: -3.0820
Max Act: 2.9081. Min Act: -0.1700
Data Index: 3296457 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0820. Min Range: -3.0820
Max Act: 2.9240. Min Act: -0.1700
Data Index: 8077379 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0820. Min Range: -3.0820
Max Act: 2.9240. Min Act: -0.1700
Data Index: 4100246 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0820. Min Range: -3.0820
Max Act: 2.9240. Min Act: -0.1700
Data Index: 6671741 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0820. Min Range: -3.0820
Max Act: 2.9240. Min Act: -0.1700
Data Index: 785363 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0820. Min Range: -3.0820
Max Act: 2.9240. Min Act: -0.1700
Data Index: 3229246 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #19