Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4305 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0804. Min Range: -5.0804
Max Act: 5.0804. Min Act: -0.1700
Data Index: 7013166 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0804. Min Range: -5.0804
Max Act: 4.9866. Min Act: -0.1700
Data Index: 6032724 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0804. Min Range: -5.0804
Max Act: 4.8616. Min Act: -0.1700
Data Index: 462850 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0804. Min Range: -5.0804
Max Act: 4.6741. Min Act: -0.1700
Data Index: 7006142 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0804. Min Range: -5.0804
Max Act: 4.6741. Min Act: -0.1700
Data Index: 1065947 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0804. Min Range: -5.0804
Max Act: 4.6741. Min Act: -0.1700
Data Index: 4228719 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0804. Min Range: -5.0804
Max Act: 4.6429. Min Act: -0.1700
Data Index: 4059795 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0804. Min Range: -5.0804
Max Act: 4.6429. Min Act: -0.1700
Data Index: 4049458 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0804. Min Range: -5.0804
Max Act: 4.6429. Min Act: -0.1700
Data Index: 1781719 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0804. Min Range: -5.0804
Max Act: 4.6429. Min Act: -0.1700
Data Index: 3052660 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0804. Min Range: -5.0804
Max Act: 4.6116. Min Act: -0.1700
Data Index: 8038424 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0804. Min Range: -5.0804
Max Act: 4.6116. Min Act: -0.1700
Data Index: 3652090 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0804. Min Range: -5.0804
Max Act: 4.6116. Min Act: -0.1700
Data Index: 7221352 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0804. Min Range: -5.0804
Max Act: 4.5491. Min Act: -0.1700
Data Index: 1426325 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0804. Min Range: -5.0804
Max Act: 4.5491. Min Act: -0.1700
Data Index: 4718763 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0804. Min Range: -5.0804
Max Act: 4.5491. Min Act: -0.1700
Data Index: 7413625 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0804. Min Range: -5.0804
Max Act: 4.4866. Min Act: -0.1700
Data Index: 993144 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0804. Min Range: -5.0804
Max Act: 4.4866. Min Act: -0.1700
Data Index: 6202461 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0804. Min Range: -5.0804
Max Act: 4.4866. Min Act: -0.1700
Data Index: 3781933 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0804. Min Range: -5.0804
Max Act: 4.4866. Min Act: -0.1700
Data Index: 6857576 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #19