Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5609 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.5646. Min Range: -9.5646
Max Act: 9.5021. Min Act: -0.1700
Data Index: 1984292 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5646. Min Range: -9.5646
Max Act: 9.5646. Min Act: -0.1700
Data Index: 4561564 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5646. Min Range: -9.5646
Max Act: 9.3771. Min Act: -0.1700
Data Index: 2776347 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5646. Min Range: -9.5646
Max Act: 9.2521. Min Act: -0.1700
Data Index: 4036556 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5646. Min Range: -9.5646
Max Act: 9.1271. Min Act: -0.1700
Data Index: 22987 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5646. Min Range: -9.5646
Max Act: 9.0646. Min Act: -0.1700
Data Index: 7693021 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5646. Min Range: -9.5646
Max Act: 9.0646. Min Act: -0.1700
Data Index: 1301551 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5646. Min Range: -9.5646
Max Act: 9.0646. Min Act: -0.1699
Data Index: 4392901 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5646. Min Range: -9.5646
Max Act: 8.9396. Min Act: -0.1700
Data Index: 893261 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5646. Min Range: -9.5646
Max Act: 8.9396. Min Act: -0.1700
Data Index: 3643710 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5646. Min Range: -9.5646
Max Act: 8.8771. Min Act: -0.1700
Data Index: 2468293 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5646. Min Range: -9.5646
Max Act: 8.8771. Min Act: -0.1700
Data Index: 8727573 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5646. Min Range: -9.5646
Max Act: 8.8771. Min Act: -0.1700
Data Index: 2005986 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5646. Min Range: -9.5646
Max Act: 8.8146. Min Act: -0.1700
Data Index: 8762701 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5646. Min Range: -9.5646
Max Act: 8.8146. Min Act: -0.1699
Data Index: 5779680 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5646. Min Range: -9.5646
Max Act: 8.7521. Min Act: -0.1700
Data Index: 3005801 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5646. Min Range: -9.5646
Max Act: 8.7521. Min Act: -0.1700
Data Index: 3328107 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5646. Min Range: -9.5646
Max Act: 8.7521. Min Act: -0.1700
Data Index: 4297031 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5646. Min Range: -9.5646
Max Act: 8.8146. Min Act: -0.1698
Data Index: 4087716 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5646. Min Range: -9.5646
Max Act: 8.7521. Min Act: -0.1700
Data Index: 7325093 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #19