Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5136 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 17.4828. Min Range: -17.4828
Max Act: 17.4828. Min Act: -0.1700
Data Index: 8319614 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 17.4828. Min Range: -17.4828
Max Act: 17.2328. Min Act: -0.1700
Data Index: 5564834 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 17.4828. Min Range: -17.4828
Max Act: 17.2328. Min Act: -0.1700
Data Index: 7272054 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 17.4828. Min Range: -17.4828
Max Act: 17.1078. Min Act: -0.1700
Data Index: 520807 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 17.4828. Min Range: -17.4828
Max Act: 16.9828. Min Act: -0.1700
Data Index: 4079904 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 17.4828. Min Range: -17.4828
Max Act: 17.1078. Min Act: -0.1700
Data Index: 4812512 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 17.4828. Min Range: -17.4828
Max Act: 17.1078. Min Act: -0.1700
Data Index: 8806947 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 17.4828. Min Range: -17.4828
Max Act: 17.1078. Min Act: -0.1700
Data Index: 8169499 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 17.4828. Min Range: -17.4828
Max Act: 16.9828. Min Act: -0.1700
Data Index: 2111231 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 17.4828. Min Range: -17.4828
Max Act: 16.9828. Min Act: -0.1700
Data Index: 1678780 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 17.4828. Min Range: -17.4828
Max Act: 16.9828. Min Act: -0.1700
Data Index: 6436052 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 17.4828. Min Range: -17.4828
Max Act: 16.9828. Min Act: -0.1700
Data Index: 5624214 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 17.4828. Min Range: -17.4828
Max Act: 16.9828. Min Act: -0.1700
Data Index: 4988006 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 17.4828. Min Range: -17.4828
Max Act: 16.9828. Min Act: -0.1700
Data Index: 3927143 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 17.4828. Min Range: -17.4828
Max Act: 16.8578. Min Act: -0.1700
Data Index: 3548305 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 17.4828. Min Range: -17.4828
Max Act: 16.8578. Min Act: -0.1700
Data Index: 416544 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 17.4828. Min Range: -17.4828
Max Act: 16.8578. Min Act: -0.1700
Data Index: 3626074 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 17.4828. Min Range: -17.4828
Max Act: 16.8578. Min Act: -0.1700
Data Index: 3836417 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 17.4828. Min Range: -17.4828
Max Act: 16.8578. Min Act: -0.1700
Data Index: 3847539 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 17.4828. Min Range: -17.4828
Max Act: 16.8578. Min Act: -0.1700
Data Index: 3886715 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #19