Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2811 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6113. Min Range: -5.6113
Max Act: 5.6113. Min Act: -0.1700
Data Index: 3416950 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6113. Min Range: -5.6113
Max Act: 5.5175. Min Act: -0.1700
Data Index: 1170118 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6113. Min Range: -5.6113
Max Act: 5.5175. Min Act: -0.1700
Data Index: 2372547 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6113. Min Range: -5.6113
Max Act: 5.4238. Min Act: -0.1700
Data Index: 3681649 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6113. Min Range: -5.6113
Max Act: 5.4238. Min Act: -0.1700
Data Index: 778543 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6113. Min Range: -5.6113
Max Act: 5.3300. Min Act: -0.1700
Data Index: 6740096 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6113. Min Range: -5.6113
Max Act: 5.3300. Min Act: -0.1700
Data Index: 4439686 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6113. Min Range: -5.6113
Max Act: 5.2988. Min Act: -0.1700
Data Index: 153369 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6113. Min Range: -5.6113
Max Act: 5.2675. Min Act: -0.1700
Data Index: 2995213 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6113. Min Range: -5.6113
Max Act: 5.2675. Min Act: -0.1700
Data Index: 2162070 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6113. Min Range: -5.6113
Max Act: 5.2675. Min Act: -0.1700
Data Index: 3105647 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6113. Min Range: -5.6113
Max Act: 5.2988. Min Act: -0.1700
Data Index: 4750852 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6113. Min Range: -5.6113
Max Act: 5.2675. Min Act: -0.1700
Data Index: 6281520 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6113. Min Range: -5.6113
Max Act: 5.2050. Min Act: -0.1700
Data Index: 6748410 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6113. Min Range: -5.6113
Max Act: 5.2050. Min Act: -0.1700
Data Index: 8768914 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6113. Min Range: -5.6113
Max Act: 5.1738. Min Act: -0.1700
Data Index: 1247321 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6113. Min Range: -5.6113
Max Act: 5.1738. Min Act: -0.1700
Data Index: 968005 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6113. Min Range: -5.6113
Max Act: 5.1425. Min Act: -0.1700
Data Index: 1027302 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6113. Min Range: -5.6113
Max Act: 5.1425. Min Act: -0.1700
Data Index: 5218900 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6113. Min Range: -5.6113
Max Act: 5.1425. Min Act: -0.1700
Data Index: 754505 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #19