Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4019 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6985. Min Range: -7.6985
Max Act: 7.6985. Min Act: -0.1700
Data Index: 6694878 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6985. Min Range: -7.6985
Max Act: 7.5735. Min Act: -0.1700
Data Index: 2134963 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6985. Min Range: -7.6985
Max Act: 7.6047. Min Act: -0.1700
Data Index: 70300 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6985. Min Range: -7.6985
Max Act: 7.5735. Min Act: -0.1700
Data Index: 2382123 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6985. Min Range: -7.6985
Max Act: 7.5422. Min Act: -0.1700
Data Index: 4471283 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6985. Min Range: -7.6985
Max Act: 7.5110. Min Act: -0.1700
Data Index: 8046686 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6985. Min Range: -7.6985
Max Act: 7.5110. Min Act: -0.1700
Data Index: 2373925 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6985. Min Range: -7.6985
Max Act: 7.5110. Min Act: -0.1700
Data Index: 821920 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6985. Min Range: -7.6985
Max Act: 7.5110. Min Act: -0.1700
Data Index: 983459 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6985. Min Range: -7.6985
Max Act: 7.5110. Min Act: -0.1700
Data Index: 3838698 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6985. Min Range: -7.6985
Max Act: 7.4797. Min Act: -0.1700
Data Index: 5704688 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6985. Min Range: -7.6985
Max Act: 7.5110. Min Act: -0.1700
Data Index: 3170598 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6985. Min Range: -7.6985
Max Act: 7.4797. Min Act: -0.1700
Data Index: 2134965 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6985. Min Range: -7.6985
Max Act: 7.4485. Min Act: -0.1700
Data Index: 5704689 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6985. Min Range: -7.6985
Max Act: 7.4485. Min Act: -0.1700
Data Index: 7653773 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6985. Min Range: -7.6985
Max Act: 7.3860. Min Act: -0.1700
Data Index: 7224320 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6985. Min Range: -7.6985
Max Act: 7.4172. Min Act: -0.1700
Data Index: 835859 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6985. Min Range: -7.6985
Max Act: 7.4172. Min Act: -0.1700
Data Index: 681577 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6985. Min Range: -7.6985
Max Act: 7.4172. Min Act: -0.1700
Data Index: 7899796 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6985. Min Range: -7.6985
Max Act: 7.4172. Min Act: -0.1700
Data Index: 955640 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #19