Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6309 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6750. Min Range: -6.6750
Max Act: 6.6750. Min Act: -0.1700
Data Index: 5420889 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6750. Min Range: -6.6750
Max Act: 6.3312. Min Act: -0.1700
Data Index: 7177902 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6750. Min Range: -6.6750
Max Act: 5.9250. Min Act: -0.1700
Data Index: 4422090 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6750. Min Range: -6.6750
Max Act: 5.8937. Min Act: -0.1700
Data Index: 483672 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6750. Min Range: -6.6750
Max Act: 5.8625. Min Act: -0.1700
Data Index: 1987561 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6750. Min Range: -6.6750
Max Act: 5.8312. Min Act: -0.1700
Data Index: 5847582 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6750. Min Range: -6.6750
Max Act: 5.7687. Min Act: -0.1700
Data Index: 6867522 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6750. Min Range: -6.6750
Max Act: 5.8312. Min Act: -0.1700
Data Index: 3172796 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6750. Min Range: -6.6750
Max Act: 5.8000. Min Act: -0.1700
Data Index: 4677775 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6750. Min Range: -6.6750
Max Act: 5.8000. Min Act: -0.1700
Data Index: 8624984 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6750. Min Range: -6.6750
Max Act: 5.7687. Min Act: -0.1700
Data Index: 5307488 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6750. Min Range: -6.6750
Max Act: 5.7687. Min Act: -0.1700
Data Index: 662668 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6750. Min Range: -6.6750
Max Act: 5.7687. Min Act: -0.1700
Data Index: 8208892 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6750. Min Range: -6.6750
Max Act: 5.7062. Min Act: -0.1700
Data Index: 6347666 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6750. Min Range: -6.6750
Max Act: 5.7375. Min Act: -0.1700
Data Index: 7060234 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6750. Min Range: -6.6750
Max Act: 5.7062. Min Act: -0.1700
Data Index: 6122218 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6750. Min Range: -6.6750
Max Act: 5.7062. Min Act: -0.1700
Data Index: 3947989 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6750. Min Range: -6.6750
Max Act: 5.6750. Min Act: -0.1700
Data Index: 4015440 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6750. Min Range: -6.6750
Max Act: 5.6437. Min Act: -0.1700
Data Index: 4322992 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6750. Min Range: -6.6750
Max Act: 5.6437. Min Act: -0.1700
Data Index: 7157266 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #19