Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3021 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1051. Min Range: -6.1051
Max Act: 6.1051. Min Act: -0.1700
Data Index: 2875713 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1051. Min Range: -6.1051
Max Act: 6.0739. Min Act: -0.1700
Data Index: 3392480 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1051. Min Range: -6.1051
Max Act: 6.0114. Min Act: -0.1700
Data Index: 8184623 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1051. Min Range: -6.1051
Max Act: 5.8551. Min Act: -0.1700
Data Index: 7730994 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1051. Min Range: -6.1051
Max Act: 5.8239. Min Act: -0.1700
Data Index: 7990055 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1051. Min Range: -6.1051
Max Act: 5.7926. Min Act: -0.1700
Data Index: 5740994 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1051. Min Range: -6.1051
Max Act: 5.7614. Min Act: -0.1700
Data Index: 3354502 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1051. Min Range: -6.1051
Max Act: 5.7614. Min Act: -0.1700
Data Index: 1674710 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1051. Min Range: -6.1051
Max Act: 5.7301. Min Act: -0.1700
Data Index: 3401190 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1051. Min Range: -6.1051
Max Act: 5.6989. Min Act: -0.1700
Data Index: 6230398 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1051. Min Range: -6.1051
Max Act: 5.7301. Min Act: -0.1700
Data Index: 7308633 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1051. Min Range: -6.1051
Max Act: 5.7301. Min Act: -0.1700
Data Index: 6289153 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1051. Min Range: -6.1051
Max Act: 5.6989. Min Act: -0.1700
Data Index: 8647054 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1051. Min Range: -6.1051
Max Act: 5.6989. Min Act: -0.1700
Data Index: 525144 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1051. Min Range: -6.1051
Max Act: 5.6676. Min Act: -0.1700
Data Index: 7449065 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1051. Min Range: -6.1051
Max Act: 5.6364. Min Act: -0.1700
Data Index: 3052566 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1051. Min Range: -6.1051
Max Act: 5.6364. Min Act: -0.1700
Data Index: 5842777 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1051. Min Range: -6.1051
Max Act: 5.6051. Min Act: -0.1700
Data Index: 4872891 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1051. Min Range: -6.1051
Max Act: 5.5739. Min Act: -0.1700
Data Index: 8051982 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1051. Min Range: -6.1051
Max Act: 5.6051. Min Act: -0.1700
Data Index: 249686 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #19