Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3250 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2646. Min Range: -4.2646
Max Act: 4.2646. Min Act: -0.1699
Data Index: 3719259 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2646. Min Range: -4.2646
Max Act: 3.9833. Min Act: -0.1700
Data Index: 1209776 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2646. Min Range: -4.2646
Max Act: 3.9833. Min Act: -0.1676
Data Index: 2888919 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2646. Min Range: -4.2646
Max Act: 3.9208. Min Act: -0.1698
Data Index: 2141645 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2646. Min Range: -4.2646
Max Act: 3.8895. Min Act: -0.1700
Data Index: 1250692 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2646. Min Range: -4.2646
Max Act: 3.8895. Min Act: -0.1700
Data Index: 584571 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2646. Min Range: -4.2646
Max Act: 3.8270. Min Act: -0.1685
Data Index: 1475769 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2646. Min Range: -4.2646
Max Act: 3.8270. Min Act: -0.1700
Data Index: 4677101 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2646. Min Range: -4.2646
Max Act: 3.8270. Min Act: -0.1700
Data Index: 4367829 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2646. Min Range: -4.2646
Max Act: 3.8270. Min Act: -0.1700
Data Index: 3947090 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2646. Min Range: -4.2646
Max Act: 3.8270. Min Act: -0.1700
Data Index: 3687828 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2646. Min Range: -4.2646
Max Act: 3.7957. Min Act: -0.1700
Data Index: 2573257 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2646. Min Range: -4.2646
Max Act: 3.7644. Min Act: -0.1700
Data Index: 1481507 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2646. Min Range: -4.2646
Max Act: 3.7644. Min Act: -0.1700
Data Index: 542375 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2646. Min Range: -4.2646
Max Act: 3.7331. Min Act: -0.1700
Data Index: 2491335 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2646. Min Range: -4.2646
Max Act: 3.7644. Min Act: -0.1700
Data Index: 298463 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2646. Min Range: -4.2646
Max Act: 3.7331. Min Act: -0.1700
Data Index: 6076815 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2646. Min Range: -4.2646
Max Act: 3.7018. Min Act: -0.1700
Data Index: 5780577 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2646. Min Range: -4.2646
Max Act: 3.7018. Min Act: -0.1700
Data Index: 2713778 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2646. Min Range: -4.2646
Max Act: 3.7331. Min Act: -0.1699
Data Index: 6196459 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #19