Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3070 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3970. Min Range: -7.3970
Max Act: 7.3970. Min Act: -0.1700
Data Index: 3830707 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3970. Min Range: -7.3970
Max Act: 7.2720. Min Act: -0.1700
Data Index: 4269 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3970. Min Range: -7.3970
Max Act: 7.2095. Min Act: -0.1700
Data Index: 5693479 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3970. Min Range: -7.3970
Max Act: 7.2408. Min Act: -0.1700
Data Index: 6433359 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3970. Min Range: -7.3970
Max Act: 7.2095. Min Act: -0.1700
Data Index: 2585728 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3970. Min Range: -7.3970
Max Act: 7.1783. Min Act: -0.1700
Data Index: 1597200 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3970. Min Range: -7.3970
Max Act: 7.1470. Min Act: -0.1700
Data Index: 6218326 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3970. Min Range: -7.3970
Max Act: 7.1158. Min Act: -0.1700
Data Index: 1049421 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3970. Min Range: -7.3970
Max Act: 7.1158. Min Act: -0.1700
Data Index: 3430695 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3970. Min Range: -7.3970
Max Act: 7.0845. Min Act: -0.1700
Data Index: 7413906 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3970. Min Range: -7.3970
Max Act: 7.0220. Min Act: -0.1700
Data Index: 5839135 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3970. Min Range: -7.3970
Max Act: 6.9595. Min Act: -0.1700
Data Index: 1652780 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3970. Min Range: -7.3970
Max Act: 6.9595. Min Act: -0.1700
Data Index: 6370233 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3970. Min Range: -7.3970
Max Act: 6.9595. Min Act: -0.1700
Data Index: 3480594 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3970. Min Range: -7.3970
Max Act: 6.9595. Min Act: -0.1700
Data Index: 5517795 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3970. Min Range: -7.3970
Max Act: 6.8658. Min Act: -0.1700
Data Index: 6942274 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3970. Min Range: -7.3970
Max Act: 6.8658. Min Act: -0.1700
Data Index: 7706940 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3970. Min Range: -7.3970
Max Act: 6.8658. Min Act: -0.1700
Data Index: 8247556 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3970. Min Range: -7.3970
Max Act: 6.8658. Min Act: -0.1700
Data Index: 5390527 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3970. Min Range: -7.3970
Max Act: 6.8658. Min Act: -0.1700
Data Index: 5178149 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #19