Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2892 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3743. Min Range: -7.3743
Max Act: 7.3743. Min Act: -0.1700
Data Index: 6896772 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3743. Min Range: -7.3743
Max Act: 7.3431. Min Act: -0.1700
Data Index: 6079323 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3743. Min Range: -7.3743
Max Act: 7.1556. Min Act: -0.1700
Data Index: 3234860 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3743. Min Range: -7.3743
Max Act: 7.1556. Min Act: -0.1697
Data Index: 3140022 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3743. Min Range: -7.3743
Max Act: 7.1243. Min Act: -0.1700
Data Index: 4343292 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3743. Min Range: -7.3743
Max Act: 7.0931. Min Act: -0.1700
Data Index: 2587046 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3743. Min Range: -7.3743
Max Act: 7.0618. Min Act: -0.1700
Data Index: 7438053 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3743. Min Range: -7.3743
Max Act: 7.0306. Min Act: -0.1700
Data Index: 4675602 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3743. Min Range: -7.3743
Max Act: 7.0306. Min Act: -0.1700
Data Index: 3871285 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3743. Min Range: -7.3743
Max Act: 6.9993. Min Act: -0.1700
Data Index: 1160914 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3743. Min Range: -7.3743
Max Act: 6.9993. Min Act: -0.1700
Data Index: 7438059 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3743. Min Range: -7.3743
Max Act: 6.9993. Min Act: -0.1700
Data Index: 2566019 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3743. Min Range: -7.3743
Max Act: 6.9993. Min Act: -0.1698
Data Index: 5812292 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3743. Min Range: -7.3743
Max Act: 6.9993. Min Act: -0.1689
Data Index: 1064166 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3743. Min Range: -7.3743
Max Act: 6.9993. Min Act: -0.1700
Data Index: 2587048 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3743. Min Range: -7.3743
Max Act: 6.9681. Min Act: -0.1700
Data Index: 7876625 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3743. Min Range: -7.3743
Max Act: 6.9993. Min Act: -0.1700
Data Index: 2261751 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3743. Min Range: -7.3743
Max Act: 6.9056. Min Act: -0.1700
Data Index: 6123930 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3743. Min Range: -7.3743
Max Act: 6.9056. Min Act: -0.1700
Data Index: 5532826 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3743. Min Range: -7.3743
Max Act: 6.8743. Min Act: -0.1700
Data Index: 6613099 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #19