Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3709 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.3021. Min Range: -4.3021
Max Act: 4.3021. Min Act: -0.1700
Data Index: 6506433 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3021. Min Range: -4.3021
Max Act: 4.2083. Min Act: -0.1700
Data Index: 1965109 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3021. Min Range: -4.3021
Max Act: 4.0833. Min Act: -0.1700
Data Index: 5727218 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3021. Min Range: -4.3021
Max Act: 4.0208. Min Act: -0.1700
Data Index: 5595124 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3021. Min Range: -4.3021
Max Act: 3.9895. Min Act: -0.1700
Data Index: 3661846 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3021. Min Range: -4.3021
Max Act: 3.9739. Min Act: -0.1700
Data Index: 1224703 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3021. Min Range: -4.3021
Max Act: 3.9426. Min Act: -0.1700
Data Index: 7147300 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3021. Min Range: -4.3021
Max Act: 3.9426. Min Act: -0.1700
Data Index: 7181839 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3021. Min Range: -4.3021
Max Act: 3.9270. Min Act: -0.1700
Data Index: 15706 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3021. Min Range: -4.3021
Max Act: 3.9270. Min Act: -0.1700
Data Index: 6846871 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3021. Min Range: -4.3021
Max Act: 3.8957. Min Act: -0.1700
Data Index: 1632480 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3021. Min Range: -4.3021
Max Act: 3.8801. Min Act: -0.1700
Data Index: 5601632 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3021. Min Range: -4.3021
Max Act: 3.8957. Min Act: -0.1700
Data Index: 4133533 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3021. Min Range: -4.3021
Max Act: 3.8957. Min Act: -0.1700
Data Index: 3729178 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3021. Min Range: -4.3021
Max Act: 3.8801. Min Act: -0.1700
Data Index: 8089159 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3021. Min Range: -4.3021
Max Act: 3.8957. Min Act: -0.1700
Data Index: 1382208 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3021. Min Range: -4.3021
Max Act: 3.8644. Min Act: -0.1700
Data Index: 7099601 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3021. Min Range: -4.3021
Max Act: 3.8644. Min Act: -0.1700
Data Index: 1404146 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3021. Min Range: -4.3021
Max Act: 3.8644. Min Act: -0.1700
Data Index: 3786716 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3021. Min Range: -4.3021
Max Act: 3.8332. Min Act: -0.1700
Data Index: 1560649 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #19