Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4522 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7082. Min Range: -7.7082
Max Act: 7.7082. Min Act: -0.1700
Data Index: 4180782 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7082. Min Range: -7.7082
Max Act: 7.6457. Min Act: -0.1700
Data Index: 3506522 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7082. Min Range: -7.7082
Max Act: 7.4582. Min Act: -0.1700
Data Index: 7431584 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7082. Min Range: -7.7082
Max Act: 7.4582. Min Act: -0.1700
Data Index: 3941757 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7082. Min Range: -7.7082
Max Act: 7.4582. Min Act: -0.1700
Data Index: 7706227 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7082. Min Range: -7.7082
Max Act: 7.3019. Min Act: -0.1700
Data Index: 6427582 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7082. Min Range: -7.7082
Max Act: 7.3019. Min Act: -0.1700
Data Index: 3859646 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7082. Min Range: -7.7082
Max Act: 7.2394. Min Act: -0.1700
Data Index: 7686669 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7082. Min Range: -7.7082
Max Act: 7.2082. Min Act: -0.1700
Data Index: 1150178 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7082. Min Range: -7.7082
Max Act: 7.2082. Min Act: -0.1700
Data Index: 7263814 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7082. Min Range: -7.7082
Max Act: 7.2082. Min Act: -0.1700
Data Index: 7042443 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7082. Min Range: -7.7082
Max Act: 7.1769. Min Act: -0.1700
Data Index: 4944563 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7082. Min Range: -7.7082
Max Act: 7.1769. Min Act: -0.1700
Data Index: 6507024 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7082. Min Range: -7.7082
Max Act: 7.0832. Min Act: -0.1700
Data Index: 1350521 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7082. Min Range: -7.7082
Max Act: 7.1144. Min Act: -0.1700
Data Index: 8167700 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7082. Min Range: -7.7082
Max Act: 7.1144. Min Act: -0.1700
Data Index: 5243294 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7082. Min Range: -7.7082
Max Act: 7.0832. Min Act: -0.1700
Data Index: 7073097 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7082. Min Range: -7.7082
Max Act: 7.0832. Min Act: -0.1700
Data Index: 602708 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7082. Min Range: -7.7082
Max Act: 7.0519. Min Act: -0.1700
Data Index: 4417022 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7082. Min Range: -7.7082
Max Act: 7.1144. Min Act: -0.1700
Data Index: 5048638 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #19